How to make on-device speech recognition practical

Branching encoder networks make operation more efficient, while “neural diffing” reduces bandwidth requirements for model updates.

Historically, Alexa’s automatic-speech-recognition models, which convert speech to text, have run in the cloud. But in recent years, we’ve been working to move more of Alexa’s computational capacity to the edge of the network — to Alexa-enabled devices themselves.

The move to the edge promises faster response times, since data doesn’t have to travel to and from the cloud; lower consumption of Internet bandwidth, which is important in some applications; and availability on devices with inconsistent Internet connections, such as Alexa-enabled in-car sound systems.

At this year’s Interspeech, we and our colleagues presented two papers describing some of the innovations we’re introducing to make it practical to run Alexa at the edge.

In one paper, “Amortized neural networks for low-latency speech recognition”, we show how to reduce the computational cost of neural-network-based automatic speech recognition (ASR) by 45% with no loss in accuracy. Our method also has lower latencies than similar methods for reducing computation, meaning that it enables Alexa to respond more quickly to customer requests.

In the other paper, “Learning a neural diff for speech models”, we show how to dramatically reduce the bandwidth required to update neural models on the edge. Instead of transmitting a complete model, we transmit a set of updates for some select parameters. In our experiments, this reduced the size of the update by as much as 98% with negligible effect on model accuracy.

Amortized neural networks

Neural ASR models are usually encoder-decoder models. The input to the encoder is a sequence of short speech snippets called frames, which the encoder converts into a representation that’s useful for decoding. The decoder translates that representation into text.

Neural encoders can be massive, requiring millions of computations for each input. But much of a speech signal is uninformative, consisting of pauses between syllables or redundant sounds. Passing uninformative frames through a huge encoder is just wasted computation.

Our approach is to use multiple encoders, of differing complexity, and decide on the fly which should handle a given frame of speech. That decision is made by a small neural network called an arbitrator, which must process every input frame before it’s encoded. The arbitrator adds some computational overhead to the process, but the time savings from using a leaner encoder is more than enough to offset it.

Researchers have tried similar approaches in domains other than speech, but when they trained their models, they minimized the average complexity of the frame-encoding process. That leaves open the possibility that the last few frames of the signal may pass to the more complex encoder, causing delays (increasing latency).

Both processing flows above (a and b) distribute the same number of frames to the fast and slow (F and S) encoders, respectively, resulting in the same average computational cost. But the top flow incurs a significantly higher latency.

In our paper, we propose a new loss function that adds a penalty (Lamr in the figure above) for routing frames to the fast encoder when we don’t have a significant audio backlog. Without the penalty term, our branched-encoder model reduces latency to 29 to 234 milliseconds, versus thousands of milliseconds for models with a single encoder. But adding the penalty term cuts latency even further, to the 2-to-9-millisecond range.

The audio backlog is one of the factors that the arbitrator considers when deciding which encoder should receive a given frame of audio.

In our experiments, we used two encoders, one complex and one lean, although in principle, our approach could generalize to larger numbers of encoders.

We train the arbitrator and both encoders together, end to end. During training, the same input passes through both encoders, and based on the accuracy of the resulting speech transcription, the arbitrator learns a probability distribution, which describes how often it should route frames with certain characteristics to the slow or fast encoder.

Over multiple epochs — multiple passes through the training data — we turn up the “temperature” on the arbitrator, skewing the distribution it learns more dramatically. In the first epoch, the split for a certain type of frame might be 70%-30% toward one encoder or the other. After three or four epochs, however, all of the splits are more like 99.99%-0.01% — essentially binary classifications.

We used three baselines in our experiments, all of which were single-encoder models. One was the full-parameter model, and the other two were compressed versions of the same model. One of these was compressed through sparsification (pruning of nonessential network weights), the other through matrix factorization (decomposing the model’s weight matrix into two smaller matrices that are multiplied together). 

Against the baselines, we compared two versions of our model, which were compressed through the same two methods. We ran all the models on a single-threaded processor at 650 million FLOPs per second.

Our sparse model had the lowest latency —two milliseconds, compared to 3,410 to 6,154 milliseconds for the baselines — and our matrix factorization model required the fewest number of floating-point operations per frame — 23 million, versus 30 million to 43 million for the baselines. Our accuracy remained comparable, however — a word error rate of 8.6% to 8.7%, versus 8.5% to 8.7% for the baselines.

Neural diffs

The ASR models that power Alexa are constantly being updated. During the Olympics, for instance, we anticipated a large spike in requests that used words like “Ledecky” and “Kalisz” and updated our models accordingly.

With cloud-based ASR, when we’ve updated a model, we simply send copies of it to a handful of servers in a data center. But with edge ASR, we may ultimately need to send updates to millions of devices simultaneously. So one of our research goals is to minimize the bandwidth requirements for edge updates.

In our other Interspeech paper, we borrow an idea from software engineering — that of the diff, or a file that charts the differences between the previous version of a codebase and the current one.

Our idea was that, if we could develop the equivalent of a diff for neural networks, we could use it to update on-device ASR models, rather than having to transmit all the parameters of a complete network with every update.

We experimented with two different approaches to creating a diff, matrix sparsification and hashing. With matrix sparsification we begin with two matrices of the same size, one that represents the weights of the connections in the existing ASR model and one that’s all zeroes.

Then, when we retrain the ASR model on new data, we update, not the parameters of the old model, but the entries in the second matrix — the diff. The updated model is a linear combination of the original weights and the values in the diff.

Over successive training epochs, we prune the entries of matrices with too many non-zeroes, gradually sparsifying the diff.

When training the diff, we use an iterative procedure that prunes matrices with too many non-zero entries. As we did when training the arbitrator in the branched-encoder network, we turn up the temperature over successive epochs to make the diff sparser and sparser.

Our other approach to creating diffs was to use a hash function, a function that maps a large number of mathematical objects to a much smaller number of storage locations, or “buckets”. Hash functions are designed to distribute objects evenly across buckets, regardless of the objects’ values.

With this approach, we hash the locations in the diff matrix to buckets, and then, during training, we update the values in the buckets, rather than the values in the matrices. Since each bucket corresponds to multiple locations in the diff matrix, this reduces the amount of data we need to transfer to update a model. 

Hashed diffing.jpg
With hash diffing, a small number of weights (in the hash buckets at bottom) are used across a matrix with a larger number of entries.
Credit: Glynis Condon

One of the advantages of our approach, relative to other approaches to compression, such as matrix factorization, is that with each update, our diffs can target a different set of model weights. By contrast, traditional compression methods will typically lock you into modifying the same set of high-importance weights with each update.

An advantage of our diffing approach is that we can target a different set of weights with each model update, which gives us more flexibility in adapting to a changing data landscape.

In our experiments, we investigated the effects of three to five consecutive model updates, using different diffs for each. Hash diffing sometimes worked better for the first few updates, but over repeated iterations, models updated through hash diffing diverged more from full-parameter models. With sparsification diffing, the word error rate of a model updated five times in a row was less than 1% away from that of the full-parameter model, with diffs whose size was set at 10% of the full model’s.

Related content

US, WA, Seattle
Are you excited about building high-performance robotic systems that can perceive, learn, and act intelligently alongside humans? The Robotics AI team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.The Amazon Robotics team is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. Come join us!
US, VA, Arlington
The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. As Director for PXT Central Science Technology, you will be responsible for leading multiple teams through rapidly evolving complex demands and define, develop, deliver and execute on our science roadmap and vision. You will provide thought leadership to scientists and engineers to invent and implement scalable machine learning recommendations and data driven algorithms supporting flexible UI frameworks. You will manage and be responsible for delivering some of our most strategic technical initiatives. You will design, develop and operate new, highly scalable software systems that support Amazon’s efforts to be Earth’s Best Employer and have a significant impact on Amazon’s commitment to our employees and communities where we both serve and employ 1.3 million Amazonians. As Director of Applied Science, you will be part of the larger technical leadership community at Amazon. This community forms the backbone of the company, plays a critical role in the broad business planning, works closely with senior executives to develop business targets and resource requirements, influences our long-term technical and business strategy, helps hire and develop engineering leaders and developers, and ultimately enables us to deliver engineering innovations.This role is posted for Arlington, VA, but we are flexible on location at many of our offices in the US and Canada.
US, VA, Arlington
Employer: Services LLCPosition: Data Scientist IILocation: Arlington, VAMultiple Positions Available1. Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.2. Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.3. Leverage big data to explore and introduce areas of analytics and technologies.4. Analyze data to identify opportunities to impact populations.5. Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.6. Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.7. Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.8. Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools. #0000
US, TX, Dallas
Employer: Services LLCPosition: Data Scientist II (multiple positions available)Location: Dallas, TX Multiple Positions Available:1. Assist customers to deliver Machine Learning (ML) and Deep Learning (DL) projects from beginning to end, by aggregating data, exploring data, building and validating predictive models, and deploying completed models to deliver business impact to the organization;2. Apply understanding of the customer’s business need and guide them to a solution using AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances;3. Use Deep Learning frameworks like MXNet, PyTorch, Caffe 2, Tensorflow, Theano, CNTK, and Keras to help our customers build DL models;4. Research, design, implement and evaluate novel computer vision algorithms and ML/DL algorithms;5. Work with data architects and engineers to analyze, extract, normalize, and label relevant data;6. Work with DevOps engineers to help customers operationalize models after they are built;7. Assist customers with identifying model drift and retraining models;8. Research and implement novel ML and DL approaches, including using FPGA;9. Develop computer vision and machine learning methods and algorithms to address real-world customer use-cases; and10. Design and run experiments, research new algorithms, and work closely with engineers to put algorithms and models into practice to help solve customers' most challenging problems.11. Approximately 15% domestic and international travel required.12. Telecommuting benefits are available.#0000
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Manager III, Data ScienceLocation: Bellevue, WashingtonPosition Responsibilities:Manage a team of data scientists working to build large-scale, technical solutions to increase effectiveness of Amazon Fulfillment systems. Define key business goals and map them to the success of technical solutions. Aggregate, analyze and model data from multiple sources to inform business decisions. Manage and quantify improvement in the customer experience resulting from research outcomes. Develop and manage a long-term research vision and portfolio of research initiatives, with algorithms and models that to be integrated in production systems. Hire and mentor junior is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, VA, Arlington
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist IILocation: Arlington, VirginiaPosition Responsibilities:Design and implement scalable and reliable approaches to support or automate decision making throughout the business. Apply a range of data science techniques and tools combined with subject matter expertise to solve difficult business problems and cases in which the solution approach is unclear. Acquire data by building the necessary SQL / ETL queries. Import processes through various company specific interfaces for accessing Oracle, RedShift, and Spark storage systems. Build relationships with stakeholders and counterparts. Analyze data for trends and input validity by inspecting univariate distributions, exploring bivariate relationships, constructing appropriate transformations, and tracking down the source and meaning of anomalies. Build models using statistical modeling, mathematical modeling, econometric modeling, network modeling, social network modeling, natural language processing, machine learning algorithms, genetic algorithms, and neural networks. Validate models against alternative approaches, expected and observed outcome, and other business defined key performance indicators. Implement models that comply with evaluations of the computational demands, accuracy, and reliability of the relevant ETL processes at various stages of is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, IL, Chicago
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist ILocation: Chicago, IllinoisPosition Responsibilities:Build the core intelligence, insights, and algorithms that support the real estate acquisition strategies for Amazon physical stores. Tackle cutting-edge, complex problems such as predicting the optimal location for new Amazon stores by bringing together numerous data assets, and using best-in-class modeling solutions to extract the most information out of them. Work with business stakeholders, software development engineers, and other data scientists across multiple teams to develop innovative solutions at massive is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, WA, Bellevue
How do you design and provide right incentives for millions of sellers that inbound and ship billions of customer orders? How do you measure sellers' response to /causal impacts of capacity control policies we implemented at Amazon using the state-of-the-art econometric techniques? How do you optimize Amazon’s third-party supply chain using new ideas never implemented at this scale to benefit millions of customers worldwide? How do you design and evaluate seller assistance to drive their success? If these type of questions get your mind racing, we want to hear from you.Supply Chain Optimization Technologies (SCOT) optimizes Amazon’s global supply chain end to end and build systems to deliver billions of products to our customers’ doorsteps faster every year while saving hundreds of millions of dollars using economics, operational research, machine learning, and scalable distributed software on the Cloud. Fulfillment by Amazon (FBA) is an Amazon service for our marketplace third party sellers, where our sellers leverage our world-class facilities and provide customers Prime delivery promise on all their goods.We are looking for the next outstanding economist to join our interdisciplinary team of data scientists, research scientists, applied scientists, economists. The ideal candidate combines econometric acumen with strong business judgment. You have versatile modeling skills and are comfortable extracting insights from observational and experimental data. You translate insights into action through proofs-of-concept and partnerships with engineers and data scientists to productionize. You are excited to learn from and alongside seasoned analysts, scientists, engineers, and business leaders. You are an excellent communicator and effectively translate business ideas and technical findings into business action (and customer delight).Key job responsibilitiesProvide data-driven guidance and recommendations on strategic questions facing the FBA leadershipDesign and implement V0 models and experiments to kickstart new initiatives, thinking, and drive system-level changes across AmazonHelp build a long-term research agenda to understand, break down, and tackle the most stubborn and ambiguous business challengesInfluence business leaders and work closely with other scientists at Amazon to deliver measurable progress and change
US, WA, Seattle
Are you motivated to explore research in ambiguous spaces? Are you interested in conducting research that will improve the employee and manager experience at Amazon? Do you want to work on an interdisciplinary team of scientists that collaborate rather than compete? Join us at PXT Central Science!The People eXperience and Technology Central Science Team (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal.We are seeking a senior Applied Scientist with expertise in more than one or more of the following areas: machine learning, natural language processing, computational linguistics, algorithmic fairness, statistical inference, causal modeling, reinforcement learning, Bayesian methods, predictive analytics, decision theory, recommender systems, deep learning, time series modeling. In this role, you will lead and support research efforts within all aspects of the employee lifecycle: from candidate identification to recruiting, to onboarding and talent management, to leadership and development, to finally retention and brand advocacy upon exit.The ideal candidate should have strong problem-solving skills, excellent business acumen, the ability to work independently and collaboratively, and have an expertise in both science and engineering. The ideal candidate is not methods-driven, but driven by the research question at hand; in other words, they will select the appropriate method for the problem, rather than searching for questions to answer with a preferred method. The candidate will need to navigate complex and ambiguous business challenges by asking the right questions, understanding what methodologies to employ, and communicating results to multiple audiences (e.g., technical peers, functional teams, business leaders).About the teamWe are a collegial and multidisciplinary team of researchers in People eXperience and Technology (PXT) that combines the talents of science and engineering to develop innovative solutions to make Amazon Earth's Best Employer. We leverage data and rigorous analysis to help Amazon attract, retain, and develop one of the world’s largest and most talented workforces.
US, WA, Bellevue
Job summaryThe Global Supply Chain-ACES organization aims to raise the bar on Amazon’s customer experience by delivering holistic solutions for Global Customer Fulfillment that facilitate the effective and efficient movement of product through our supply chain. We develop strategies, processes, material handling and technology solutions, reporting and other mechanisms, which are simple, technology enabled, globally scalable, and locally relevant. We achieve this through cross-functional partnerships, listening to the needs of our customers and prioritizing initiatives to deliver maximum impact across the value chain. Within the organization, our Quality team balances tactical operation with operations partners with global engagement on programs to deliver improved inventory accuracy in our network. The organization is looking for an experienced Principal Research Scientist to partner with senior leadership to develop long term strategic solutions. As a Principal Scientist, they will lead critical initiatives for Global Supply Chain, leveraging complex data analysis and visualization to:a. Collaborate with business teams to define data requirements and processes;b. Automate data pipelines;c. Design, develop, and maintain scalable (automated) reports and dashboards that track progress towards plans;d. Define, track and report program success metrics.e. Serve as a technical science lead on our most demanding, cross-functional projects.