The science behind Amazon’s spatial audio-processing technology

Combining psychoacoustics, signal processing, and speaker beamforming enhances stereo audio and delivers an immersive sound experience for customers.

With every new Echo device and upgrade, we challenge ourselves to bring the best audio experience to our customers at an affordable price. This year, we’re introducing Amazon’s own custom-built spatial audio-processing technology, designed to enhance stereo sound on compatible Echo devices.

The version of the technology on Echo Studio, for instance, is customized to the specific acoustic design of the speakers and employs digital-processing methods — such as upmixing and virtualization — so stereo audio, television shows, and movie soundtracks feel closer to the listener, with greater width, clarity, and presence. It turns the Echo Studio into a hi-fi audio system that mirrors that of a stereo reference arrangement. Vocal performances are more present in the center soundstage, and stereo panned instruments are better defined on the sides, thereby creating a more immersive sound experience that reproduces the artist's intent.

In this blog post, we break down how we built this spatial audio-processing technology with an emphasis on the way humans perceive sound — or psychoacoustics — by using a combination of crosstalk cancellation, speaker beamforming, and upmixing to create a room-filling, spatial audio experience.

Psychoacoustics: Width, depth, and listening zones

Throughout development, we characterize the stereo image by its psychoacoustic qualities, including width, depth, and listening zones. We then investigate how sound waves interact with listeners in various room shapes and sizes and how signal-processing methods affect the listener’s experience.

Stereo angle.png
Echo Studio virtualizes the stereo sound field at the listener’s location in the far field.

Width

Width: The angular extent (wide vs. narrow) of localizable elements in the stereo image along the horizontal — or azimuth — plane.

When determining the width of a sound field, we first consider localizable elements such as a point-source that would induce time and level differences in the acoustic responses at the listener’s two ears. To model this phenomenon, it is helpful to compare the listening experiences on headphones vs. a loudspeaker in terms of the separation of left and right ear responses.

Unlike loudspeaker listening, headphone listening lacks a crosstalk path, as illustrated in the image below. In order to make headphone listening realistic, we can model crosstalk from the point-source to the two ears using an all-pass signal-processing filter for one ear and a delayed low-pass filter for the other ear. The two filters approximate and parameterize the listener’s ear responses with respect to their relative head-related transfer functions (HRTFs), which contain important cues that the human ear uses to localize sound. Moreover, the filter design ensures that there’s minimal modification to the signal spectra — or tonal balance — and therefore preserves the original playback content.

Crosstalk simulation.png
All-pass and delayed low-pass filters approximate the angle-dependent relative ipsilateral (same side of the body) and contralateral (opposite side of the body) head-related transfer functions (HRTFs).

However, unlike headphones, an external speaker can create its own crosstalk for the listener, depending on its placement. For example, the left and right speaker transducers, or drivers, on the Echo Studio are narrowly spaced within the device, whereas the speakers in a standard stereo pair are 60 degrees apart relative to the listener.

With the spatial audio-processing technology on Echo Studio, we decouple the crosstalk of the driver pair by modeling and then inverting the system of equations between each driver and the listener’s ears, via crosstalk cancellation (CTC) methods. If we have more than two drivers, then the more general formulation is called null-steering, where filters are designed for all the drivers so that their acoustic responses cancel at one ear.

In both cases, we can normalize the filter design to satisfy a target cancellation gain curve defined by the power ratio of the acoustic energy at the ipsilateral (same side of the body) and contralateral (opposite side of the body) ears across frequencies. This prevents overfitting the cancellation to an exact location, since a listener may be at varying distances or not perfectly centered to the device.

Once the driver’s CTC filters are designed for stereo inputs, they can be combined with the approximated HRTF filters that introduce the amount of crosstalk consistent with a stereo reference system.

CTC filters.png
Stereo virtualization for external speaker playback specifies an additional pair of crosstalk cancellation (CTC) filters for nulling the contralateral acoustic response. The relative transfer function (RTF) filter realizes the ratio of the two CTC filter responses.

Depth

Depth: The distance (frontal vs. recessed) of the perceived sound field from the listener.

The distance at which sound elements in an audio track localize correlates with the relationship — or coherence — of the two signals between the sound source and the listener’s ears. For example, a simple left or right signal from a speaker is easy to understand, but if the audio mixes with the room’s reverberation, the audio clarity decreases, and the audio sounds recessed.

In speaker playback, however, we contend with the speaker directivity and its interaction with the room environment. For example, a direct acoustic path between a speaker and a listener preserves the desired clarity of the original content. But when the acoustic signal reflects off of walls, the loss in coherence recesses the perceived sound field and causes elements to smear spatially. This is why tracks heard anechoically or on headphones appear closer — or even inside the listener’s head — and clearer than tracks heard over external speakers in a reverberant room. In the first case, the acoustic response is direct from the driver to the listener’s ears, while external speakers must contend with the effects of the room environment.

Beamformer impact.png
Strong room reflections and reverberation mask the binaural cues and reduce the perceived distance of the soundstage. Speaker beamforming pushes the soundstage forward by attenuating the indirect sound energy, increasing the critical distance and coherence.

As part of our custom-built spatial audio technology, we can control the speaker directivity via careful beamforming. The speaker drivers can be filtered to produce a sound field with a directivity that sums coherently on-axis and cancels off-axis. That is, the acoustic response is greatest when the listener is lined up in front of the speaker and, conversely, weakest when the listener is to the side at +/- 90 degrees.

Therefore, one way to design with such directivity is to place two nulls at +/- 90-degree angles and either control for the cancellation gain between on-/off-axis power responses or the shape of the nulls as a function of azimuth. The resulting beam pattern is one with a main lobe that is wide enough for the direct path to be strong, at up to a +/- 45-degree azimuth listening window, before quickly tapering off to minimize the acoustic energy further off-axis, which would reflect off the walls.

This has the intended effect of making stereo audio feel closer to the listener, with greater clarity than is typical in an acoustically untreated listening environment like a living room. The effect is similar to how theaters reproduce a frontal soundstage over different seating areas, despite the speakers’ being far away.

Beamforming.png
The speaker beamformer increases directivity after placing two off-axis nulls in the midrange frequencies. The acoustic responses over frequency and azimuth contrast that of simple matrix mixing with the beamformer realized in relative-transfer-function (RTF) form.

Listening zones

Listening zone: The mapping between the listening area and the stereo soundstage.

A listening “sweet spot” — the stereo image in a hi-fi audio system reference stereo pair — is best reproduced when the listener’s location forms an equilateral triangle with the stereo speaker pair. If the listener angle exceeds +/- 30 degrees, then a hole is created in the listener’s phantom center due to the loss of inter-speaker-to-ear coherence as room reflections grow stronger. Important elements of the audio mix, such as vocals, lose their presence. If the listener angle falls below +/- 30 degrees, then the stereo image narrows, as audio elements collapse toward the center. If the listener’s location is off-axis, then the stereo image biases towards one side or the other.

Phantom center.png
The stereo field relies on a “phantom center”, where important lead vocals and instruments are mixed. The center content can be separated from the original stereo left and right input after the mid-/side decomposition.

To combat this, our spatial audio technology aims to reproduce the stereo image over the largest listening area. In practice, the intended listening area of CTC-filtered playback conflicts with that of beamforming designs that control for speaker directivity. We can achieve a compromise by performing stereo upmixing and then applying different beamforming filters to each channel. For example, we can upmix into left, right, and center (LRC), where the center is minimally correlated with left-minus-right in the mid-/side decomposition.

The upmixed left channel is processed through the CTC filter that nulls the right ear after virtualization, the upmixed right channel nulls the left ear, and the center channel is beamformed with a wide main lobe. This means that vocal performances are more present in the center, while the stereo panned instruments are better defined on the side, creating a more immersive sound experience for the listener.

Signal flow.png
After upmixing, the virtualization and the crosstalk cancellation (CTC) widens the left and right channels, and the midrange beamformer pushes the center content forward. Subsequent delay blocks phase-align the faster of the two paths.

We’re continuing to iterate and refine technology across the Echo portfolio to bring the best audio experience to our customers. If you’d like to learn more about beamforming and speaker directivity in room acoustics, read papers published by our engineering team: “Fast source-room-receiver modeling”, in EUSIPCO 2020, and “Spherical harmonic beamformer designs", in EURASIP 2021.

Research areas

Related content

US, WA, Seattle
Do you want to re-invent how millions of people consume video content on their TVs, Tablets and Alexa? We are building a free to watch streaming service called Fire TV Channels (https://techcrunch.com/2023/08/21/amazon-launches-fire-tv-channels-app-400-fast-channels/). Our goal is to provide customers with a delightful and personalized experience for consuming content across News, Sports, Cooking, Gaming, Entertainment, Lifestyle and more. You will work closely with engineering and product stakeholders to realize our ambitious product vision. You will get to work with Generative AI and other state of the art technologies to help build personalization and recommendation solutions from the ground up. You will be in the driver's seat to present customers with content they will love. Using Amazon’s large-scale computing resources, you will ask research questions about customer behavior, build state-of-the-art models to generate recommendations and run these models to enhance the customer experience. You will participate in the Amazon ML community and mentor Applied Scientists and Software Engineers with a strong interest in and knowledge of ML. Your work will directly benefit customers and you will measure the impact using scientific tools.
US, MA, Boston
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to build industry-leading technology with Large Language Models (LLMs) and multi-modal systems. You will support projects that work on technologies including multi-modal model alignment, moderation systems and evaluation. Key job responsibilities As an Applied Scientist with the AGI team, you will support the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. 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 generative artificial intelligence (GenAI). You are also expected to publish in top tier conferences. About the team The AGI team has a mission to push the envelope in LLMs and multimodal systems. Specifically, we focus on model alignment with an aim to maintain safety while not denting utility, in order to provide the best-possible experience for our customers.
IN, HR, Gurugram
Our customers have immense faith in our ability to deliver packages timely and as expected. A well planned network seamlessly scales to handle millions of package movements a day. It has monitoring mechanisms that detect failures before they even happen (such as predicting network congestion, operations breakdown), and perform proactive corrective actions. When failures do happen, it has inbuilt redundancies to mitigate impact (such as determine other routes or service providers that can handle the extra load), and avoids relying on single points of failure (service provider, node, or arc). Finally, it is cost optimal, so that customers can be passed the benefit from an efficiently set up network. Amazon Shipping is hiring Applied Scientists to help improve our ability to plan and execute package movements. As an Applied Scientist in Amazon Shipping, you will work on multiple challenging machine learning problems spread across a wide spectrum of business problems. You will build ML models to help our transportation cost auditing platforms effectively audit off-manifest (discrepancies between planned and actual shipping cost). You will build models to improve the quality of financial and planning data by accurately predicting ship cost at a package level. Your models will help forecast the packages required to be pick from shipper warehouses to reduce First Mile shipping cost. Using signals from within the transportation network (such as network load, and velocity of movements derived from package scan events) and outside (such as weather signals), you will build models that predict delivery delay for every package. These models will help improve buyer experience by triggering early corrective actions, and generating proactive customer notifications. Your role will require you to demonstrate Think Big and Invent and Simplify, by refining and translating Transportation domain-related business problems into one or more Machine Learning problems. You will use techniques from a wide array of machine learning paradigms, such as supervised, unsupervised, semi-supervised and reinforcement learning. Your model choices will include, but not be limited to, linear/logistic models, tree based models, deep learning models, ensemble models, and Q-learning models. You will use techniques such as LIME and SHAP to make your models interpretable for your customers. You will employ a family of reusable modelling solutions to ensure that your ML solution scales across multiple regions (such as North America, Europe, Asia) and package movement types (such as small parcel movements and truck movements). You will partner with Applied Scientists and Research Scientists from other teams in US and India working on related business domains. Your models are expected to be of production quality, and will be directly used in production services. You will work as part of a diverse data science and engineering team comprising of other Applied Scientists, Software Development Engineers and Business Intelligence Engineers. You will participate in the Amazon ML community by authoring scientific papers and submitting them to Machine Learning conferences. You will mentor Applied Scientists and Software Development Engineers having a strong interest in ML. You will also be called upon to provide ML consultation outside your team for other problem statements. If you are excited by this charter, come join us!
IN, HR, Gurugram
We're on a journey to build something new a green field project! Come join our team and build new discovery and shopping products that connect customers with their vehicle of choice. We're looking for a talented Senior Applied Scientist to join our team of product managers, designers, and engineers to design, and build innovative automotive-shopping experiences for our customers. This is a great opportunity for an experienced engineer to design and implement the technology for a new Amazon business. We are looking for a Applied Scientist to design, implement and deliver end-to-end solutions. We are seeking passionate, hands-on, experienced and seasoned Senior Applied Scientist who will be deep in code and algorithms; who are technically strong in building scalable computer vision machine learning systems across item understanding, pose estimation, class imbalanced classifiers, identification and segmentation.. You will drive ideas to products using paradigms such as deep learning, semi supervised learning and dynamic learning. As a Senior Applied Scientist, you will also help lead and mentor our team of applied scientists and engineers. You will take on complex customer problems, distill customer requirements, and then deliver solutions that either leverage existing academic and industrial research or utilize your own out-of-the-box but pragmatic thinking. In addition to coming up with novel solutions and prototypes, you will directly contribute to implementation while you lead. A successful candidate has excellent technical depth, scientific vision, project management skills, great communication skills, and a drive to achieve results in a unified team environment. You should enjoy the process of solving real-world problems that, quite frankly, haven’t been solved at scale anywhere before. Along the way, we guarantee you’ll get opportunities to be a bold disruptor, prolific innovator, and a reputed problem solver—someone who truly enables AI and robotics to significantly impact the lives of millions of consumers. Key job responsibilities Architect, design, and implement Machine Learning models for vision systems on robotic platforms Optimize, deploy, and support at scale ML models on the edge. Influence the team's strategy and contribute to long-term vision and roadmap. Work with stakeholders across , science, and operations teams to iterate on design and implementation. Maintain high standards by participating in reviews, designing for fault tolerance and operational excellence, and creating mechanisms for continuous improvement. Prototype and test concepts or features, both through simulation and emulators and with live robotic equipment Work directly with customers and partners to test prototypes and incorporate feedback Mentor other engineer team members. A day in the life - 6+ years of building machine learning models for retail application experience - PhD, or Master's degree and 6+ years of applied research experience - Experience programming in Java, C++, Python or related language - Experience with neural deep learning methods and machine learning - Demonstrated expertise in computer vision and machine learning techniques.
US, MA, Boston
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Senior Applied Scientist with a strong deep learning background, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Senior Applied Scientist with the AGI team, you will work with talented peers to lead the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. 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 generative artificial intelligence (GenAI). About the team The AGI team has a mission to push the envelope in LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
IN, KA, Bengaluru
The Amazon Alexa AI team in India is seeking a talented, self-driven Applied Scientist to work on prototyping, optimizing, and deploying ML algorithms within the realm of Generative AI. Key responsibilities include: - Research, experiment and build Proof Of Concepts advancing the state of the art in AI & ML for GenAI. - Collaborate with cross-functional teams to architect and execute technically rigorous AI projects. - Thrive in dynamic environments, adapting quickly to evolving technical requirements and deadlines. - Engage in effective technical communication (written & spoken) with coordination across teams. - Conduct thorough documentation of algorithms, methodologies, and findings for transparency and reproducibility. - Publish research papers in internal and external venues of repute - Support on-call activities for critical issues Basic Qualifications: - Master’s or PhD in computer science, statistics or a related field or relevant science experience (publications/scientific prototypes) in lieu of Masters - Experience in deep learning, machine learning, and data science. - Proficiency in coding and software development, with a strong focus on machine learning frameworks. - Experience in Python, or another language; command line usage; familiarity with Linux and AWS ecosystems. - Understanding of relevant statistical measures such as confidence intervals, significance of error measurements, development and evaluation data sets, etc. - Excellent communication skills (written & spoken) and ability to collaborate effectively in a distributed, cross-functional team setting. Preferred Qualifications: - Track record of diving into data to discover hidden patterns and conducting error/deviation analysis - Ability to develop experimental and analytic plans for data modeling processes, use of strong baselines, ability to accurately determine cause and effect relations - The motivation to achieve results in a fast-paced environment. - Exceptional level of organization and strong attention to detail - Comfortable working in a fast paced, highly collaborative, dynamic work environment - Papers published in AI/ML venues of repute
IN, KA, Bengaluru
The Amazon Alexa AI team in India is seeking a talented, self-driven Applied Scientist to work on prototyping, optimizing, and deploying ML algorithms within the realm of Generative AI. Key responsibilities include: - Research, experiment and build Proof Of Concepts advancing the state of the art in AI & ML for GenAI. - Collaborate with cross-functional teams to architect and execute technically rigorous AI projects. - Thrive in dynamic environments, adapting quickly to evolving technical requirements and deadlines. - Engage in effective technical communication (written & spoken) with coordination across teams. - Conduct thorough documentation of algorithms, methodologies, and findings for transparency and reproducibility. - Publish research papers in internal and external venues of repute - Support on-call activities for critical issues Basic Qualifications: - Master’s or PhD in computer science, statistics or a related field - 2-7 years experience in deep learning, machine learning, and data science. - Proficiency in coding and software development, with a strong focus on machine learning frameworks. - Experience in Python, or another language; command line usage; familiarity with Linux and AWS ecosystems. - Understanding of relevant statistical measures such as confidence intervals, significance of error measurements, development and evaluation data sets, etc. - Excellent communication skills (written & spoken) and ability to collaborate effectively in a distributed, cross-functional team setting. - Papers published in AI/ML venues of repute Preferred Qualifications: - Track record of diving into data to discover hidden patterns and conducting error/deviation analysis - Ability to develop experimental and analytic plans for data modeling processes, use of strong baselines, ability to accurately determine cause and effect relations - The motivation to achieve results in a fast-paced environment. - Exceptional level of organization and strong attention to detail - Comfortable working in a fast paced, highly collaborative, dynamic work environment
IN, KA, Bengaluru
Amazon is investing heavily in building a world class advertising business and we are responsible for defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products. We are highly motivated, collaborative and fun-loving with an entrepreneurial spirit and bias for action. With a broad mandate to experiment and innovate, we are growing at an unprecedented rate with a seemingly endless range of new opportunities. The ATT team, based in Bangalore, is responsible for ensuring that ads are relevant and is of good quality, leading to higher conversion for the sellers and providing a great experience for the customers. We deal with one of the world’s largest product catalog, handle billions of requests a day with plans to grow it by order of magnitude and use automated systems to validate tens of millions of offers submitted by thousands of merchants in multiple countries and languages. In this role, you will build and develop ML models to address content understanding problems in Ads. These models will rely on a variety of visual and textual features requiring expertise in both domains. These models need to scale to multiple languages and countries. You will collaborate with engineers and other scientists to build, train and deploy these models. As part of these activities, you will develop production level code that enables moderation of millions of ads submitted each day.
US, WA, Seattle
The Search Supply & Experiences team, within Sponsored Products, is seeking an Applied Scientist to solve challenging problems in natural language understanding, personalization, and other areas using the latest techniques in machine learning. In our team, you will have the opportunity to create new ads experiences that elevate the shopping experience for our hundreds of millions customers worldwide. As an Applied Scientist, you will partner with other talented scientists and engineers to design, train, test, and deploy machine learning models. You will be responsible for translating business and engineering requirements into deliverables, and performing detailed experiment analysis to determine how shoppers and advertisers are responding to your changes. We are looking for candidates who thrive in an exciting, fast-paced environment and who have a strong personal interest in learning, researching, and creating new technologies with high customer impact. Key job responsibilities As an Applied Scientist on the Search Supply & Experiences team you will: - Perform hands-on analysis and modeling of enormous datasets to develop insights that increase traffic monetization and merchandise sales, without compromising the shopper experience. - Drive end-to-end machine learning projects that have a high degree of ambiguity, scale, and complexity. - Build machine learning models, perform proof-of-concept, experiment, optimize, and deploy your models into production; work closely with software engineers to assist in productionizing your ML models. - Design and run experiments, gather data, and perform statistical analysis. - Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving. - Stay up to date on the latest advances in machine learning. About the team We are a customer-obsessed team of engineers, technologists, product leaders, and scientists. We are focused on continuous exploration of contexts and creatives where advertising delivers value to shoppers and advertisers. We specifically work on new ads experiences globally with the goal of helping shoppers make the most informed purchase decision. We obsess about our customers and we are continuously innovating on their behalf to enrich their shopping experience on Amazon
US, WA, Seattle
Have you ever wondered how Amazon launches and maintains a consistent customer experience across hundreds of countries and languages it serves its customers? Are you passionate about data and mathematics, and hope to impact the experience of millions of customers? Are you obsessed with designing simple algorithmic solutions to very challenging problems? If so, we look forward to hearing from you! At Amazon, we strive to be Earth's most customer-centric company, where both internal and external customers can find and discover anything they want in their own language of preference. Our Translations Services (TS) team plays a pivotal role in expanding the reach of our marketplace worldwide and enables thousands of developers and other stakeholders (Product Managers, Program Managers, Linguists) in developing locale specific solutions. Amazon Translations Services (TS) is seeking an Applied Scientist to be based in our Seattle office. As a key member of the Science and Engineering team of TS, this person will be responsible for designing algorithmic solutions based on data and mathematics for translating billions of words annually across 130+ and expanding set of locales. The successful applicant will ensure that there is minimal human touch involved in any language translation and accurate translated text is available to our worldwide customers in a streamlined and optimized manner. With access to vast amounts of data, cutting-edge technology, and a diverse community of talented individuals, you will have the opportunity to make a meaningful impact on the way customers and stakeholders engage with Amazon and our platform worldwide. Together, we will drive innovation, solve complex problems, and shape the future of e-commerce. Key job responsibilities * Apply your expertise in LLM models to design, develop, and implement scalable machine learning solutions that address complex language translation-related challenges in the eCommerce space. * Collaborate with cross-functional teams, including software engineers, data scientists, and product managers, to define project requirements, establish success metrics, and deliver high-quality solutions. * Conduct thorough data analysis to gain insights, identify patterns, and drive actionable recommendations that enhance seller performance and customer experiences across various international marketplaces. * Continuously explore and evaluate state-of-the-art modeling techniques and methodologies to improve the accuracy and efficiency of language translation-related systems. * Communicate complex technical concepts effectively to both technical and non-technical stakeholders, providing clear explanations and guidance on proposed solutions and their potential impact. About the team We are a start-up mindset team. As the long-term technical strategy is still taking shape, there is a lot of opportunity for this fresh Science team to innovate by leveraging Gen AI technoligies to build scalable solutions from scratch. Our Vision: Language will not stand in the way of anyone on earth using Amazon products and services. Our Mission: We are the enablers and guardians of translation for Amazon's customers. We do this by offering hands-off-the-wheel service to all Amazon teams, optimizing translation quality and speed at the lowest cost possible.