What Is the Role of Science in Alexa?

Science is critical to how Alexa is revolutionizing daily conveniences, from playing music and controlling your smart home, to getting information and much more just by using your voice. Our scientists and engineers develop foundational AI technologies for anyone to build intelligent conversational interfaces for any device, application, language or environment. We build machine learning algorithms, services and data-driven models for key components, such as wake word detection, automatic speech recognition, natural language understanding, contextual reasoning, dialog management, question answering, and text-to-speech, all of which contribute to the magic that is Alexa.

What Is Our Unique Approach to Science?

We believe in hiring and developing world-class talent in science and engineering, and building teams with multi-disciplinary skills with clear charters and goals. These multi-disciplinary teams employ our working backwards method to identify key long-term problems to solve on behalf of our customers and a staged approach to ensuring we make rapid progress towards our goals. The combination of world-class elastic computing resources available via AWS, large-scale heterogeneous data resources, and the team’s years of experience in building and deploying machine learning algorithms is key to innovation at scale.

What Is the Impact?

Our research is focused on delivering magical experiences for our customers through the ground-breaking Echo family of devices and third-party devices available everywhere. As a result, our conversational AI inventions are having a direct impact on the lives of millions of people. We also contribute to the advancement of conversational AI through engagements with the academic community via funded research and Grand Challenges such as the Alexa Prize. Moreover, we encourage the publication of research that will contribute to the future of AI.

Research published recently by Alexa conversational AI scientists includes:

• Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates, Interspeech 2018, Joo-Kyung Kim, Young-Bum Kim
• A simple model for detection of rare sound events, Interspeech 2018, Weiran Wang, Chieh-Chi Kao, Chao Wang
• R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection, Interspeech 2018, Chieh-Chi Kao, Weiran Wang, Ming Sun, Chao Wang
• Detecting Media Sound Presence in Acoustic Scenes, Interspeech 2018, Constantinos Papayiannis, Justice Amoh, Viktor Rozgic, Shiva Sundaram, Chao Wang
• Device Directed Utterance Detection, Interspeech 2018, Sri Harish Mallidi, Roland Maas, Ariya Rastrow, Spyros Matsoukas, Björn Hoffmeister, Kyle Goehner
• Design Challenges in Named Entity Transliteration, Coling 2018, Yuval Merhav, Stephen Ash
• Contextual Language Model Adaptation for Conversational Agents, Interspeech 2018, Anirudh Raju, Behnam Hedayatnia, Ankur Gandhe, Chandra Khatri, Angeliki Metallinou, Anu Venkatesh, Ariya Rastrow, Linda Liu
• Statistical Model Compression for Small-Footprint Natural Language Understanding, Interspeech 2018, Grant Strimel, Kanthashree Mysore Sathyendra, Stanislav Peshterliev
• Play Duration based User-Entity Affinity Modeling in Spoken Dialog System, Interspeech 2018, Bo Xiao, Nicholas Monath, Shankar Ananthakrishnan, Abishek Ravi
• Contextual Slot Carryover for Disparate Schemas, Interspeech 2018, Chetan Naik, Arpit Gupta, Hancheng Ge, Lambert Mathias, Ruhi Sarikaya
• The Alexa Meaning Representation Language, NAACL 2018, Thomas Kollar, Danielle Berry, Lauren Stuart, Karolina Owczarzak, Tagyoung Chung, Lambert Mathias, Michael Kayser, Bradford Snow, Spyros Matsoukas
• Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System, NAACL 2018, Judith Gaspers, Penny Karanasou, Rajen Chatterjee
• Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents, NAACL 2018, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas
• Efficient Large-Scale Neural Domain Classification with Personalized Attention, ACL 2018, Young-Bum Kim, Dongchan Kim, Anjishnu Kumar, Ruhi Sarikaya
• A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding, NAACL 2018, Young-Bum Kim, Dongchan Kim, Joo-Kyung Kim, Ruhi Sarikaya
• Monophone-Based Background Modeling For Two-Stage On-Device Wake Word Detection, ICASSP 2018, Minhua Wu, Sankaran Panchapagesan, Ming Sun, Jiacheng Gu, Ian Thomas, Shiv Naga Prasad Vitaladevuni, Björn Hoffmeister, Arindam Mandal
• Time Delayed Bottleneck Highway Networks Using A DFT Feature For Keyword Spotting, ICASSP 2018, Jinxi Guo, Kenichi Kumatani, Ming Sun, Minhua Wu, Anirudh Raju, Nikko Strom, Arindam Mandal
• Multilayer Adaptation Based Complex Echo Cancellation and Voice Enhancement, ICASSP 2018, Jun Yang
• Combining Acoustic Embeddings and Decoding Features for End-Of-Utterance Detection in Real-Time Far-Field Speech Recognition Systems, ICASSP 2018, Roland Maas, Ariya Rastrow, Chengyuan Ma, Guitang Lan, Kyle Goehner, Gautam Tiwari, Shaun Joseph, Bjorn Hoffmeister
• Context Aware Conversational Understanding for Intelligent Agents with a Screen, AAAI 2018, Vishal Naik, Angeliki Metallinou, Rahul Goel
• Multi-Task Learning For Parsing The Alexa Meaning Representation Language, AAAI 2018, Vittorio Perera, Tagyoung Chung, Thomas Kollar, Emma Strubell