ICASSP: What “signal processing” has come to mean

Alexa scientist Ariya Rastrow on the blurring boundaries between acoustic processing and language understanding.

The International Conference on Acoustics, Speech, and Signal Processing (ICASSP), which starts today, is now in its 45th year, and according to Google Scholar’s rankings, it’s the highest-impact conference in the field of signal processing.

But as speech-related technologies have matured, the definition of signal processing has expanded. “ICASSP is a mix of a lot of different tracks,” says Ariya Rastrow, an Alexa principal research scientist who attended his first ICASSP in 2006. “It has the whole spectrum, from very low-level signal processing all the way to interpretation and natural-language understanding.”

Ariya Rastrow.png
Alexa principal research scientist Ariya Rastrow
Credit: Jordan Stead

This diversity, Rastrow explains, simply reflects that of the human audio-processing system. The brain doesn’t rely exclusively on acoustic signals to recognize words, and neither should computer systems.

“The interaction between language and acoustics is very dynamic from the human perspective,” Rastrow says. “If I’m talking to you in a very clean environment, we are capable of following on the acoustic level at very high resolution. But if we’re sitting in a noisy bar, you as a human are going to rely more on your prior — on a semantic level, what are the things that the other person might say? what are the topics that they might talk about? —and use that to enhance your recognition.”

Traditionally, the task of spoken-language understanding has been broken into two components: automatic speech recognition (ASR), which converts an acoustic speech signal into text, and natural-language understanding (NLU), which makes sense of the text.

But in fact, speech recognition usually relies on higher-level linguistic features to identify words. The traditional ASR system consists of an acoustic model, which translates acoustic signals into low-level phonetic representations; a lexicon, which maps sequences of low-level phonetic representations to words; and a language model, which uses high-level statistics about words’ co-occurrence to adjudicate between competing interpretations of the acoustic signal.

“Twenty, twenty-five years ago, there was this pragmatic idea to build factored systems,” Rastrow explains. “You have clear-cut boundaries between components of the system. Traditional speech recognition systems are built over an architecture that we call a hidden Markov model (HMM) architecture. The HMM architecture will put these multiple knowledge sources together at inference time. But the acoustic model and the language model are trained separately.”

Shared representations

Recently, however, this approach has begun to give way to end-to-end training of large, neural-network-based architectures. That is, a single neural network is trained on examples that consist of acoustic inputs and fully transcribed outputs, and it directly learns the relationships previously encoded in the ASR system’s separate components.

“This has many benefits” Rastrow says, “one being that by doing joint training you build systems that are more optimized in terms of accuracy. If you build factored systems, often you train each component for a specific objective function, and at inference time, they don’t know how to handle disfluencies and errors. By virtue of advances in architectures and doing joint training and multitask training, the systems are becoming more robust to those types of confusions.”

“That’s one benefit,” Rastrow continues. “Another is that the system gains in efficiency. By having a mechanism to do knowledge transfer, joint training, or shared representation, you get to the point where different parts of the systems can rely on the same types of representations or shared layers [of the network]. This can result in compression of the overall size of the system, execution speedups, and opportunities to deploy such systems on low-resource devices and hardware.

“For example, if you’re doing acoustic-event detection, and you’re also doing wake word detection and whisper detection, which are different types of audio-based classification tasks, one way is to build all the systems separately. The other way is that you can do knowledge transfer and shared representation learning, and by virtue of those shared network components and layers, you can gain efficiency beyond the obvious accuracy improvements.

“Also, the whole system is done in neural-network execution that we know how to accelerate both on the software and the hardware side, versus this explicit knowledge representation — lexicon versus language model. Traditionally, these are not deep-learning based, so we could not leverage these efficiency mechanisms. For the last two to three years, we have been pursuing this direction.”

Total integration

Allowing a single large model to integrate the ASR system’s low-level acoustic-signal processing and high-level language modeling raises the prospect of taking advantage of still higher-level linguistic features. In one of the 19 Amazon papers at this year’s ICASSP, for instance, Alexa researchers report using semantic features to help distinguish between utterances intended for Alexa and those that are not, where in the past, Alexa’s “device directedness” detector relied solely on acoustic features.

The end point of all this integration, of course, would be a single neural network that executed the entire task of spoken-language understanding — both ASR and NLU.

“There is emerging research that shows that at least for a subset of interactions, you can build a single, small-footprint network that can directly translate audio to the semantic level,” Rastrow says. “You get even better latency. You don’t have to do stage-wise execution. Also, there are studies showing that humans don’t do recognition word by word. We carry information on the parts of the speech that are semantically important for the topic, for the conversation.”

“But challenges remain,” Rastrow says. “These all-neural systems thrive on data. And once you move closer to the understanding layer, you have to cope more and more with data sparsity and the nuances of unique interactions. On the acoustic level, for the sound <p>, even across languages, you can get a lot of examples. But as you go closer to the semantic and sentence-level understanding, the patterns become more unique.

“One challenge is how we combine these new architectures for doing direct audio to NLU with our advances in semi-supervised learning and unsupervised learning. Another challenge is how to combine very data-oriented learning systems with some kind of reasoning or logic.

“I’ll give you an example. If you say, ‘Alexa turn on the bedroom light’, and Alexa misinterprets and turns on the kitchen light, and you follow that by saying, ‘No, Alexa, don’t turn on the kitchen light,’ now you have the negation problem. When you say ‘Don’t turn it on’, you really mean ‘Turn it off’. It is very hard to find those examples in data. Traditionally, we know how to address that problem with rules and logic and reasoning, but relying merely on data might not give us a good representation of those unique patterns. So the questions in the next two, three years of research will be how to combine those systems with either semi-supervised or unsupervised learning and how to combine them with knowledge and logic.”

About the Author
Larry Hardesty is the editor of the Amazon Science blog. Previously, he was managing editor of the Boston Book Review, a senior editor at MIT Technology Review, and the computer science writer at the MIT News Office.

Amazon publications at ICASSP

View All

Work with us

See More Jobs
US, MA, North Reading
Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart team of doers that work passionately to apply cutting edge advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even image yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling, and fun.POSITION OVERVIEWThe Technical Operations Manufacturing team at Amazon Robotics is looking for an experienced, results-oriented Data Scientist to solve difficult problems in manufacturing. The data ranges from mechanical dimensional data to results of complex electromechanical tests, with a little bit of everything in between. Our team is looking for a data scientist to derive insights from this data and communicate the results though white papers, presentations, and production ready models. This role will interface with engineers in software, hardware test, manufacturing, and design. Our methods include design of experiments, statistical modeling, machine learning, financial analysis, and data visualization in a combined team of software engineering and data science.A successful candidate should have a background in business analytics, data science, and data visualization. We are looking for jack-of-all-trades that is able to select and use the right tools to bring clarity to complex questions and help drive decisions. While we don’t assume mastery in all areas, successful team members can speak and work competently in multiple domains.The key strategic objectives for this role include:· Understanding drivers, impacts, and key influences on manufacturing failures.· Optimizing identification of defective product to improve our customer satisfaction.· Drive actions at scale to improve manufacturing yields using scientifically-based methods and decision-making.· Helping to build production systems that take inputs from multiple models and make decisions in real-time.· Automating feedback loops for algorithms in production.· Utilizing Amazon systems and tools to effectively work with terabytes of data.
US, WA, Seattle
The Team: Amazon Go is a new kind of store with no lines and no checkout—you just grab and go! Customers simply use the Amazon Go app to enter the store, take what they want from our selection of fresh, delicious meals and grocery essentials, and go!Our checkout-free shopping experience is made possible by our Just Walk Out Technology, which automatically detects when products are taken from or returned to the shelves and keeps track of them in a virtual cart. When you’re done shopping, you can just leave the store. Shortly after, we’ll charge your Amazon account and send you a receipt. Check it out at amazon.com/go. Designed and custom-built by Amazonians, our Just Walk Out Technology uses a variety of technologies including computer vision, sensor fusion, and advanced machine learning. Innovation is part of our DNA! Our goal is to be Earths’ most customer centric company and we are just getting started. We need people who want to join an ambitious program that continues to push the state of the art in computer vision, machine learning, distributed systems and hardware design.The Role: Everyone on the team needs to be entrepreneurial, wear many hats and work in a highly collaborative environment that’s more startup than big company. We’ll need to tackle problems that span a variety of domains: computer vision, image recognition, machine learning, real-time and distributed systems. Do you want to join a team of scientists who use computer vision and machine learning to keep Amazon at the frontiers of AI? Are you excited by the prospect of analyzing and modeling terabytes of data and create state-of-art algorithms to solve real world problems? Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company? Do you like to innovate and simplify? If yes, then you may be a great fit to join our Research group.Technical Responsibilities:· Lead the development and implementation of computer vision and machine learning models and algorithms· Applies advanced mathematical theory, statistical analysis and machine learning techniques to improve existing approaches and designs.· Designs solutions for complex business problems while keeping a company-wide perspective using quantitative methods· Executes highly complex projects and plays a role in key aspects of a strategic project.· Establishing efficient, automated processes for large data analyses, model development, model validation and model implementation.· Plan, design, execute and measure controlled experiments to understand impact of our actionsLeadership Responsibilities:· Understand high-level business objectives and continually align work with those objectives to meet needs of business (ROI, cost-benefit analysis).· Manage, mentor and coach researchers· Effectively advocate technical solutions to business stakeholders, engineering teams, as well as executive level decision makers.· Design strategies for effective use of model output.· Maintain a culture of innovation via rapid prototyping and research to leverage new data sources and techniques.· Leads report-writing efforts to communicate analysis and proposed solutions to stakeholders.
US, WA, Seattle
The Team: Amazon Go is a new kind of store with no lines and no checkout—you just grab and go! Customers simply use the Amazon Go app to enter the store, take what they want from our selection of fresh, delicious meals and grocery essentials, and go!Our checkout-free shopping experience is made possible by our Just Walk Out Technology, which automatically detects when products are taken from or returned to the shelves and keeps track of them in a virtual cart. When you’re done shopping, you can just leave the store. Shortly after, we’ll charge your Amazon account and send you a receipt. Check it out at amazon.com/go. Designed and custom-built by Amazonians, our Just Walk Out Technology uses a variety of technologies including computer vision, sensor fusion, and advanced machine learning. Innovation is part of our DNA! Our goal is to be Earths’ most customer centric company and we are just getting started. We need people who want to join an ambitious program that continues to push the state of the art in computer vision, machine learning, distributed systems and hardware design.The Role: Everyone on the team needs to be entrepreneurial, wear many hats and work in a highly collaborative environment that’s more startup than big company. We’ll need to tackle problems that span a variety of domains: computer vision, image recognition, machine learning, real-time and distributed systems.As an Applied Scientist, you will help solve a variety of technical challenges and mentor other scientists and engineers. Given that this is an early-stage initiative, you will play an active role in translating business and functional requirements into concrete deliverables and build quick prototypes or proofs of concept in partnership with other technology leaders within the team. You will tackle challenging, novel situations every day and given the size of this initiative, you’ll have the opportunity to work with multiple technical teams across Amazon. You should be comfortable with a degree of ambiguity that’s higher than most projects and relish the idea of solving problems that, haven’t been solved at scale before - anywhere. Along the way, we guarantee that you’ll learn a ton, have fun and make a positive impact on millions of people.
US, NY, New York
Want to help the largest global enterprises derive business value through the adoption of Artificial Intelligence (AI) and Machine Learning (ML)? Excited by using massive amounts of disparate data to develop ML models? Eager to learn to apply ML to a diverse array of enterprise use cases? Thrilled to be a part of Amazon who has been pioneering and shaping the world’s AI/ML technology for decades?At Amazon Web Services (AWS), we are helping large enterprises build ML models on the AWS Cloud. We are applying predictive technology to large volumes of data and against a wide spectrum of problems. AWS Professional Services works together with AWS customers to address their business needs using AI solutions.AWS Professional Services is a unique consulting team. We pride ourselves on being customer obsessed and highly focused on the AI enablement of our customers. If you have experience with AI, including building ML models, we’d like to have you join our team. You will get to work with an innovative company, with great teammates, and have a lot of fun helping our customers. A successful candidate will be a person who enjoys diving deep into data, doing analysis, discovering root causes, and designing long-term solutions.This is a customer-facing role and you will be required to travel to client locations and deliver professional services as needed.Major responsibilities include:· Assist customers by being able to deliver a ML project from beginning to end, including understanding the business need, aggregating data, exploring data, building & validating predictive models, and deploying completed models with concept-drift monitoring and retraining to deliver business impact to the organization· Use AWS AI services (e.g., Personalize), ML platforms (SageMaker), and frameworks (e.g., MXNet, TensorFlow, PyTorch, SparkML, scikit-learn) to help our customers build ML models· Research and implement novel ML approaches, including hardware optimizations on platforms such as AWS Inferentia· Work with our other Professional Services consultants (Big Data, IoT, HPC) to analyze, extract, normalize, and label relevant data, and with our Professional Services engineers to operationalize customers’ models after they are prototyped
US, CA, Sunnyvale
Amazon Alexa AI is looking for a passionate, talented, and inventive Scientist with a strong machine learning background to help build industry-leading Speech and Language technology. Our mission is to push the envelope in Natural Language Understanding (NLU), Audio Signal Processing, text-to-speech (TTS), and Dialog Management, in order to provide the best-possible experience for our customers.As an Applied Scientist, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art in spoken language understanding. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in spoken language understanding.
US, WA, Seattle
Amazon's Sponsored Ads is one of the fastest growing business domains and we are looking senior level scientists with experience building complex machine learning models and writing elegant prototype code. We are still in Day 1 and there is an abundance of opportunities that are yet to be explored. We are a team of highly motivated and collaborative applied scientists and software development engineers with an entrepreneurial spirit and bias for action. With the team growing at an unprecedented rate, there is broad mandate to experiment and innovate!Our systems and algorithms operate on one of the world's largest product catalogs, matching shoppers with products - with a high relevance bar and strict latency constraints. The ads sourcing works across the spectrum of ad serving including coverage expansion, increasing utilization of tail detail pages, ad relevance, ad quality, collaborative filtering, and much more. Our technology enables thousands of brands, sellers and authors to drive discovery and sales of their products at Amazon by millions of customers.We are looking for an Applied Scientists, with a background in Machine Learning to optimize serving ads on billions of product pages. The solutions you create/deploy would ensure relevant ads are served to Amazon's customers. You will directly impact the shopping experience while helping our advertisers get the maximum ROI. You will be expected to demonstrate strong ownership and should be curious to learn and leverage the rich textual, image, and other contextual signals.This role will challenge you to utilize cutting-edge machine learning techniques in the domain of predictive modeling, natural language processing (NLP), deep learning, and image recognition to deliver significant impact for the business. Ideal candidates will be able to work cross functionally across multiple stakeholders, synthesize the science needs of our business partners, develop models to solve business needs, and implement solutions in production.
US, WA, Seattle
What is the most relevant business data for AWS leadership? What are the most important insights in this data? Are we investing enough in our infrastructure, or too much? How much new workloads do our new products drive into AWS? Which initiatives help our customers utilize AWS the most? How do our customers react to changes in prices, purchase options or products?The Central AWS Econ team is dedicated to answering these questions using quantitative, economic and statistical methods. We develop cutting edge data pipelines, build accurate predictive models, and provide insights to executive leaders throughout the company. We are looking for a talented, driven, and analytical researcher to help us answer these (and many more) questions.This Data Scientist role will explore and develop innovative quantitative approaches and models, generate features, test hypotheses, and build classification and predictive models. The data scientist will work with very large, diverse, complex data sets. The successful candidate will be a problem solver who enjoys diving into data, is excited by difficult modeling challenges, and possesses strong communication skills to effectively interface between technical, finance and business teams, working together with Economists, Data Scientists, Data Engineers, Financial Analysists and Product Managers to support executive planning and decisions.Key Responsibilities:· Research, develop and build classification and predictive models based on evolving business needs· Analyze, research and develop new features and KPIs to scale new models for wider use· Provide insights by analyzing historical data
US, CA, San Francisco
The AWS Center for Quantum Computing is a multi-disciplinary team of scientists, engineers, and technicians, all working to innovate in quantum computing for the benefit of our customers. We are looking to hire a Quantum Research Scientist to understand and mitigate crosstalk and loss channels in superconducting qubit and hybrid quantum acoustic devices and their packaging. Candidates with a track record of original scientific contributions will be preferred. We are looking for candidates with strong engineering skills, resourcefulness, and a bias for action. Organization and communication skills are essential.Work/Life BalanceAt the AWS CQC, we understand that developing quantum computing technology is a marathon, not a sprint. Mental and physical wellness is encouraged within our team and throughout AWS. The work/life integration within Amazon encourages a culture where employees work hard and have ownership over their downtime. We are exploring more structured wellness elements including for example meditation, running group meet-ups, and other wellness tips.Mentorship and Career GrowthWe are committed to the growth and development of every member of the Center for Quantum Computing. You will receive career-growth-minded management and mentorship from a software and science team and also have the opportunity to participate in Amazon's science mentorship programs.Inclusive and Diverse CultureThe AWS CQC is intentional about attracting, developing, and retaining amazing talent from diverse backgrounds to build a world class team. We’re looking for a new teammate who is enthusiastic, empathetic, curious, motivated, reliable, and able to work effectively with their peers. With quantum computing being a new and growing initiative within AWS, you would have an opportunity to make an impact on our budding team culture.Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation
US, WA, Seattle
What do you like most about shopping at Amazon? Huge product selection? Amazon’s catalog has billions of items. Despite its mind-boggling size and variety, it remains the best in the business. That’s no accident! We use state of the art machine learning techniques and cloud computing technologies to keep it that way. A vast and high quality product catalog is a key strategic asset for Amazon that sets us apart from our competitors. Come help us make the world’s best product catalog even better and influence the way millions of customers shop.In this role, you will own scientific solutions to a large set of customer-facing product catalog issues that influence critical business processes and product discovery. you will have an opportunity to lead state of the art machine learning algorithms on large datasets. You will need to lead & build Amazon scale applications running on Amazon Cloud that both leverage and create new technologies to process large volumes of data that derive patterns and conclusions from the data.We are seeking an Applied Science Manager who has a strong background in applied Machine Learning and AI, deep passion for building data-driven products; ability to communicate data insights and scientific vision, and has a proven track record of leading both applied scientists and software engineers to execute complex projects and deliver business impacts.In this role, you will:· Lead a group of applied scientists to deliver machine-learning and AI solutions to production· Advance the team's craftsmanship and drive continued scientific innovation as a thought leader and practitioner· Develop science roadmaps, run monthly/quarterly/yearly planning, and foster cross-team collaboration to execute complex projects· Perform hands-on data analysis, build machine-learning models, run regular A/B tests, and communicate the impact to senior management· Hire and develop top talent, provide technical and career development guidance to both scientists and engineers in the organization
US, CA, Culver City
Prime Video is an industry leading, high-growth business and a critical driver of Amazon Prime subscriptions, which contribute to customer loyalty and lifetime value. Prime Video is used daily by a massive audience on Amazon's websites and through a variety of devices including the Kindle Fire, game consoles, smart TVs and Blu-ray players.The Prime Video Marketing Analytics team uses machine learning, econometrics, and data science to optimize Amazon’s media spending strategies on Amazon Originals and third party content, driving customer loyalty as well as enhancing lifetime value of our Prime members. We are looking for an applied data scientist to build innovative models for measuring the impact of marketing spending on customer engagement and Prime member acquisition. Key responsibilities of Prime Video applied scientists include the following:· Playing an integral role in developing a roadmap to expand and enhance marketing analytics of Prime Video· Optimizing media planning on Amazon Originals to grow Amazon Prime user engagement and acquisition· Improving model usability by analyzing customer behavior and by gathering data from business owners and other tech teams· Incorporating new data sources and implementing creative methodology innovations to improve model performance· Creating and tracking accuracy and performance metrics· Helping build production systems that take inputs from multiple models and support decision makingTo summarize, the applied scientist will join our team to generate scientific insights to guide Amazon’s digital-video marketing strategy. We use detailed customer behavioral data (e.g. streaming history) and detailed information about content (e.g. IMDb-sourced characteristics) to discern causality of advertising spending on customer engagement and Prime member acquisition, based on which we derive optimize media planning of multi-million dollar marketing budget.
US, CA, Cupertino
Are you a biochemistry research scientist? At Amazon, we are constantly inventing and re-inventing to be the most customer-centric company in the world. To get there, we need exceptionally talented, bright, and driven people. We are a smart team of doers that work passionately to apply cutting-edge advances in technology and to solve real-world problems that will transform our customers’ experiences in ways we can’t even imagine yet.As a Research Scientist, you will be working with a unique and gifted team that is developing exciting products and collaborating with cross-functional teams.Responsibilities:· Collaborate to define product specifications and protocols· Iterate through experimentation to identify optimal product parameters· Identify and qualify new materials· Ensure manufacturability across the design process· Contribute to design control and regulated protocols· Collaborate with engineering teams to design, implement, and harmonize solutions
US, CA, Cupertino
Are you a biochemistry research scientist? At Amazon, we are constantly inventing and re-inventing to be the most customer-centric company in the world. To get there, we need exceptionally talented, bright, and driven people. We are a smart team of doers that work passionately to apply cutting-edge advances in technology and to solve real-world problems that will transform our customers’ experiences in ways we can’t even imagine yet.As a Research Scientist, you will be working with a unique and gifted team that is developing exciting products and collaborating with cross-functional teams.Responsibilities:· Collaborate to define product specifications and protocols· Iterate through experimentation to identify optimal product parameters· Identify and qualify new materials· Ensure manufacturability across the design process· Contribute to design control and regulated protocols· Collaborate with engineering teams to design, implement, and harmonize solutions
US, VA, Herndon
Excited by using massive amounts of data to develop Machine Learning (ML) and Deep Learning (DL) models? Want to help public sector, medical center and non-profit agencies derive business value through the adoption of Artificial Intelligence (AI)? Eager to learn from many different enterprise’s use cases of AWS ML and DL? Thrilled to be key part of Amazon, who has been investing in Machine Learning for decades, pioneering and shaping the world’s AI technology?At Amazon Web Services (AWS), we are helping large enterprises build ML and DL models on the AWS Cloud. We are applying predictive technology to large volumes of data and against a wide spectrum of problems. Our Professional Services organization works together with our AWS customers to address their business needs using AI.AWS Professional Services is a unique consulting team. We pride ourselves on being customer obsessed and highly focused on the AI enablement of our customers. If you have experience with AI, including building ML or DL models, we’d like to have you join our team. You will get to work with an innovative company, with great teammates, and have a lot of fun helping our customers.If you do not live in a market where we have an open Data Scientist position, please feel free to apply. Our Data Scientists can live in any location where we have a Professional Service office.A successful candidate will be a person who enjoys diving deep into data, doing analysis, discovering root causes, and designing long-term solutions. It will be a person who likes to have fun, loves to learn, and wants to innovate in the world of AI. Major responsibilities include:· Understand the customer’s business need and guide them to a solution using our AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances .· Assist customers by being able to deliver a ML / DL project from beginning to end, including understanding the business need, aggregating data, exploring data, building & validating predictive models, and deploying completed models to deliver business impact to the organization.· Use Deep Learning frameworks like PyTorch, Tensorflow, and MxNet to help our customers build DL models.· Use SparkML and Amazon Machine Learning (AML) to help our customers build ML models.· Work with our Professional Services Big Data consultants to analyze, extract, normalize, and label relevant data.· Work with our Professional Services DevOps consultants to help our customers operationalize models after they are built.· Assist customers with identifying model drift and retraining models.· Research and implement novel ML and DL approaches, including using FPGA.· This position can have periods of up to 10% travel.
US, WA, Seattle
Amazon is looking for a passionate, talented, and inventive Senior Applied Scientist with a strong machine learning background to help build industry-leading Speech technology. Our mission is to push the envelope in Alexa's capability to understand customer's speech by not just transforming speech to text, but understand the non-lexical component of communication by speech, for example intonation, pitch and speed of speaking, hesitation noises, gesture, and facial expression to make Alexa more human-like.As a Scientist, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art in understanding and solving prosody. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in spoken language understanding.The ideal candidate is clearly passionate about delivering experiences that delight customers and creating solutions that are robust. Creating reliable, scalable and high performance products requires exceptional technical expertise, a sound understanding of the fundamentals of Computer Science, and practical experience building large-scale distributed systems. We value academic collaborations and encourage our scientists and engineers to publish in conferences and do open source contribution.
US, WA, Seattle
The Amazon Fashion catalog spans millions of items and variations ranging from high fashion to everyday wear. With a large, varied, and growing selection, we are looking for innovative ways to build a catalog that can drive product discovery, personalization, and a world-class customer experience.Downstream services such as recommendation engines, browse, and search experiences are dependent upon high quality and consistent catalog attributes. To optimize these inputs, we will need to manage massive quantities of data and find novel ways to apply statistics and machine learning to complex business problems.The Amazon Fashion team is looking for an experienced Applied Scientist to apply machine learning solutions to these business problems and connect customers to the products they love. You will be at the intersection of statistics, machine learning, data visualization, and business/product management. You will work closely with a multidisciplinary team to design solutions that impact millions of customers, sometimes from scratch, and apply models and algorithms in real-time systems at a very large scale.The ideal candidate is a specialist in the Natural Language Processing (NLP) domain and has a strong understanding of supervised, unsupervised and weak learning systems to quickly scale model training and inference. The candidate should be familiar with state-of-the-art techniques such as BERT and ELMo. Apart from the specialized domain, candidate should have sufficient understanding of deep learning techniques which includes applications for computer vision models. They should also be a general athlete in data with broad exposure to experimental design, modeling, working with large-scale unstructured data to uncover key insights. They should be able to ask the right questions, prioritize, and communicate/align across both technical and non-technical stakeholders. This candidate exemplifies bias for action, the desire to continuously invent and simplify, and most importantly, a genuine curiosity and passion for learning.Roles and Responsibilities:· Explore unstructured data and determine catalog improvement opportunities· Investigate the feasibility of machine learning or statistical techniques to business problems and products· Rapidly prototype with off-the-shelf machine learning models to establish baseline models· Collaborate with other scientists across teams to develop state-of-the-art performing algorithms and present technical findings to the larger science community through meetings/conferences/publications· Drive best practices, helping to set high scientific and engineering standards on the team.· Work with engineers to build requirements and productionalize models and pipelines· Communicate requirements in a way that is consumable by engineers and business stakeholders
US, WA, Seattle
The Amazon Fashion catalog spans millions of items and variations ranging from high fashion to everyday wear. With a large, varied, and growing selection, we are looking for innovative ways to build a catalog that can drive product discovery, personalization, and a world-class customer experience.Downstream services such as recommendation engines, browse, and search experiences are dependent upon high quality and consistent catalog attributes. To optimize these inputs, we will need to manage massive quantities of data and find novel ways to apply statistics and machine learning to complex business problems.The Amazon Fashion team is looking for an experienced Applied Scientist to apply machine learning solutions to these business problems and connect customers to the products they love. You will be at the intersection of statistics, machine learning, data visualization, and business/product management. You will work closely with a multidisciplinary team to design solutions that impact millions of customers, sometimes from scratch, and apply models and algorithms in real-time systems at a very large scale.The ideal candidate is a specialist in the Computer Vision (CV) domain and has a strong understanding of supervised, unsupervised and weak learning systems to quickly scale model training and inference. The candidate should be familiar with state-of-the-art techniques such as ResNet. Apart from the specialized domain, candidate should have sufficient understanding of deep learning techniques which includes applications for NLP models. They should also be a general athlete in data with broad exposure to experimental design, modeling, working with large-scale unstructured data to uncover key insights. They should be able to ask the right questions, prioritize, and communicate/align across both technical and non-technical stakeholders. This candidate exemplifies bias for action, the desire to continuously invent and simplify, and most importantly, a genuine curiosity and passion for learning.Roles and Responsibilities:· Explore unstructured data and determine catalog improvement opportunities· Investigate the feasibility of ML or statistical techniques to business problems and products· Rapidly prototype with off-the-shelf machine learning models to establish baseline models· Collaborate with other scientists across teams to develop state-of-the-art performing algorithms and present technical findings to the larger science community through meetings/conferences/publications· Drive best practices, helping to set high scientific and engineering standards on the team.· Work with engineers to build requirements and productionalize models and pipelines· Communicate requirements in a way that is consumable by engineers and business stakeholders
US, VA, Arlington
Are you passionate about networking, Big Data, machine learning and cybersecurity? Are you ready for an exciting opportunity to work with some of the best data scientists and technologies and thrive in a super dynamic environment? Do you want to help secure millions of enterprises and organizations who are running their business in cloud at an unprecedented scale?How about making a difference in making the whole Internet more secure?Amazon Web Services (AWS) is looking for data scientists to joint its cyber-security analytics team.You will leverage cutting-edge data technologies to perform statistical inference, classification, clustering, and various predictive analysis for a wide spectrum of problems in cybersecurity. As a key member of the technical team, you will translate cyber and network security related requirements into sophisticated models to help extract new insights and drive new initiatives to defend against cyber-attacks. You will be working with a large variety and huge volume of of data sets, advanced security and data technologies, and world-class operation teams to create awesome analyses for cyber security.The preferred location for this position is Baltimore, MD, but it can also be located in Herndon, VA or Arlington, VA (HQ2).
US, MD, Baltimore
Are you passionate about networking, Big Data, machine learning and cybersecurity? Are you ready for an exciting opportunity to work with some of the best data scientists and technologies and thrive in a super dynamic environment? Do you want to help secure millions of enterprises and organizations who are running their business in cloud at an unprecedented scale?How about making a difference in making the whole Internet more secure?Amazon Web Services (AWS) is looking for data scientists to joint its cyber-security analytics team.You will leverage cutting-edge data technologies to perform statistical inference, classification, clustering, and various predictive analysis for a wide spectrum of problems in cybersecurity. As a key member of the technical team, you will translate cyber and network security related requirements into sophisticated models to help extract new insights and drive new initiatives to defend against cyber-attacks. You will be working with a large variety and huge volume of of data sets, advanced security and data technologies, and world-class operation teams to create awesome analyses for cyber security.The preferred location for this position is Baltimore, MD, but it can also be located in Herndon, VA or Arlington, VA (HQ2).
US, TN, Nashville
Operations Technology ITWe develop and deliver technology that supports Amazon Operations at worldwide scope and scale that is unparalleled. We are forming a new team focused on providing advanced image solutions that leverage both automated and semi-automated Computer Vision (CV) and Machine Learning (ML) processing techniques to provide enhanced safety, productivity, and quality controls throughout Amazon’s global operation sites. We will be automating image capture and analysis, large data set handling, using convolutional neural networks (CNNs) for classification and segmentation of images, spatial recognition of objects/distance/velocity relationships, real time and near-term operational feedback loops and large-scale process automation. See Amazon’s recently open sourced Distance Assistant as a good example of our work.What You’ll DoAs a highly-skilled Data Scientist II, you’ll bring your passion for quantitative data science discipline and intellectual energy to the team to help unlock valuable information found in image data and challenge the status quo and raise the bar on every service and feature we build. You’ll apply statistics, time series analysis, stochastic modeling and machine learning to solve for critical associate wellbeing assurance, process anomaly detection and defect avoidance use cases across Amazon’s worldwide network of operational facilities, utilizing streaming and static data captured through computer vision devices linked around the globe. You’ll collaborate with cross-functional team members from multiple disciplines, including software development engineers, machine learning engineers, system development engineers, business intelligence engineers, applied scientists and operations specialists to create new data-driven solutions to challenging and meaningful problems at enormous scale.
US, WA, Seattle
Are you experienced at applying machine learning to big-data tasks? Are you excited by analyzing and modeling terabytes of text, images, and other types of data to solve real-world problems? We love data and we have lots of it. Join a high impact innovative team of scientists, economists and engineers who use Machine Learning, Statistics and Econometrics to develop highly innovative and impactful products that influence the company’s bottom line.The Central Economics team supports the executives to drive the global optimization across almost all key business units of Amazon, including market design, pricing, forecasting, online advertising, search, supply chain network planning, and other areas. Our team is building a number of highly innovative and impactful products, such as Amazon Economics Intelligence Service, Amazon Search/Discovery optimization, and Amazon Corporate Bridging Service. Join us to build revolutionary products that has significant impact of the company’s footprint. We are looking for versatile and passionate scientists who want to develop industry leading technologies and set the bar for every other company.As an applied machine learning scientist, you work with a team of scientists to drive technology and research directions. You will work on projects of large opportunities. You will collaborate with economists, engineers and product teams. Your work will have a direct impact on the bottom line of our business while improving customer experience. If big data, cutting edge technologies and building intelligent systems excite you, if you love to innovate and deliver results, then we want you to be on our team.· Use machine learning and statistics techniques to create scalable solutions for business problems· · Analyze and extract relevant information from large amounts of both structured and unstructured data to help automate and optimize key processes· · Design, experiment and evaluate highly innovative models for predictive learning· · Work closely with software engineering teams to drive real-time model experiments, implementations and new feature creations· · Work closely with business staff to optimize various business operations· · Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation· · Track general business activity and provide clear, compelling management reporting on a regular basis· · Research and implement novel machine learning, statistical and econometrics approaches