Google AI Weblog: Google at Interspeech 2022

Posted by Cat Armato, Program Supervisor, Google

This week, the twenty third Annual Convention of the Worldwide Speech Communication Affiliation (INTERSPEECH 2022) is being held in Incheon, South Korea, representing one of many world’s most intensive conferences on analysis and know-how of spoken language understanding and processing. Over 2,000 specialists in speech-related analysis fields collect to participate in oral shows and poster classes and to collaborate with streamed occasions throughout the globe.

We’re excited to be a Diamond Sponsor of INTERSPEECH 2022, the place we can be showcasing practically 50 analysis publications and supporting quite a few workshops, particular classes and tutorials. We welcome in-person attendees to drop by the Google sales space to satisfy our researchers and take part in Q&As and demonstrations of a few of our newest speech applied sciences, which assist to enhance accessibility and supply comfort in communication for billions of customers. As well as, on-line attendees are inspired to go to our digital sales space in GatherTown the place you will get up-to-date data on analysis and alternatives at Google. You may also be taught extra concerning the Google analysis being offered at INTERSPEECH 2022 beneath (Google affiliations in daring).

Organizing Committee

Business Liaisons embrace: Bhuvana Ramabahdran

Space Chairs embrace: John Hershey, Heiga Zen, Shrikanth Narayanan, Bastiaan Kleijn

ISCA Fellows

Embody: Tara Sainath, Heiga Zen

Publications

Manufacturing Federated Key phrase Recognizing by way of Distillation, Filtering, and Joint Federated-Centralized Coaching

Andrew Laborious, Kurt Partridge, Neng Chen, Sean Augenstein, Aishanee Shah, Hyun Jin Park, Alex Park, Sara Ng, Jessica Nguyen, Ignacio Lopez Moreno, Rajiv Mathews, Françoise Beaufays

Leveraging Unsupervised and Weakly-Supervised Knowledge to Enhance Direct Speech-to-Speech Translation

Ye Jia, Yifan Ding, Ankur Bapna, Colin Cherry, Yu Zhang, Alexis Conneau, Nobu Morioka

Sentence-Choose: Massive-Scale Language Mannequin Knowledge Choice for Uncommon-Phrase Speech Recognition

W. Ronny Huang, Cal Peyser, Tara N. Sainath, Ruoming Pang, Trevor Strohman, Shankar Kumar

UserLibri: A Dataset for ASR Personalization Utilizing Solely Textual content

Theresa Breiner, Swaroop Ramaswamy, Ehsan Variani, Shefali Garg, Rajiv Mathews, Khe Chai Sim, Kilol Gupta, Mingqing Chen, Lara McConnaughey

SNRi Goal Coaching for Joint Speech Enhancement and Recognition

Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani

Flip-Taking Prediction for Pure Conversational Speech

Shuo-Yiin Chang, Bo Li, Tara Sainath, Chao Zhang, Trevor Strohman, Qiao Liang, Yanzhang He

Streaming Meant Question Detection Utilizing E2E Modeling for Continued Dialog

Shuo-Yiin Chang, Guru Prakash, Zelin Wu, Tara Sainath, Bo Li, Qiao Liang, Adam Stambler, Shyam Upadhyay, Manaal Faruqui, Trevor Strohman

Bettering Distortion Robustness of Self-Supervised Speech Processing Duties with Area Adaptation


Kuan Po Huang, Yu-Kuan Fu, Yu Zhang, Hung-yi Lee

XLS-R: Self-Supervised Cross-Lingual Speech Illustration Studying at Scale


Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

Extracting Focused Coaching Knowledge from ASR Fashions, and Easy methods to Mitigate It

Ehsan Amid, Om Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays

Detecting Unintended Memorization in Language-Mannequin-Fused ASR

W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews

AVATAR: Unconstrained Audiovisual Speech Recognition

Valentin Gabeur, Paul Hongsuck Search engine marketing, Arsha Nagrani, Chen Solar, Karteek Alahari, Cordelia Schmid

Finish-to-Finish Multi-talker Audio-Visible ASR Utilizing an Energetic Speaker Consideration Module

Richard Rose, Olivier Siohan

Transformer-Primarily based Video Entrance-Ends for Audio-Visible Speech Recognition for Single and Multi-person Video

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

Unsupervised Knowledge Choice by way of Discrete Speech Illustration for ASR

Zhiyun Lu, Yongqiang Wang, Yu Zhang, Wei Han, Zhehuai Chen, Parisa Haghani

Non-parallel Voice Conversion for ASR Augmentation

Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Jesse Emond, Yinghui Huang, Pedro J. Moreno

Extremely-Low-Bitrate Speech Coding with Pre-trained Transformers


Ali Siahkoohi, Michael Chinen, Tom Denton, W. Bastiaan Kleijn, Jan Skoglund

Streaming Finish-to-Finish Multilingual Speech Recognition with Joint Language Identification

Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi, Shuo-Yiin Chang, Parisa Haghani

Bettering Deliberation by Textual content-Solely and Semi-supervised Coaching

Ke Hu, Tara N. Sainath, Yanzhang He, Rohit Prabhavalkar, Trevor Strohman, Sepand Mavandadi, Weiran Wang

E2E Segmenter: Joint Segmenting and Decoding for Lengthy-Type ASR

W. Ronny Huang, Shuo-yiin Chang, David Rybach, Rohit Prabhavalkar, Tara N. Sainath, Cyril Allauzen, Cal Peyser, Zhiyun Lu

CycleGAN-Primarily based Unpaired Speech Dereverberation

Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson

TRILLsson: Distilled Common Paralinguistic Speech Representations (see weblog submit)

Joel Shor, Subhashini Venugopalan

Studying Neural Audio Options With out Supervision


Sarthak Yadav, Neil Zeghidour

SpeechPainter: Textual content-Conditioned Speech Inpainting

Zalan Borsos, Matthew Sharifi, Marco Tagliasacchi

SpecGrad: Diffusion Probabilistic Mannequin-Primarily based Neural Vocoder with Adaptive Noise Spectral Shaping

Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani

Distance-Primarily based Sound Separation

Katharine Patterson, Kevin Wilson, Scott Knowledge, John R. Hershey

Evaluation of Self-Consideration Head Variety for Conformer-Primarily based Computerized Speech Recognition

Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno

Bettering Uncommon Phrase Recognition with LM-Conscious MWER Coaching

Wang Weiran, Tongzhou Chen, Tara Sainath, Ehsan Variani, Rohit Prabhavalkar, W. Ronny Huang, Bhuvana Ramabhadran, Neeraj Gaur, Sepand Mavandadi, Cal Peyser, Trevor Strohman, Yanzhang He, David Rybach

MAESTRO: Matched Speech Textual content Representations Via Modality Matching

Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno, Ankur Bapna, Heiga Zen

Pseudo Label is Higher Than Human Label

Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo, Trevor Strohman

On the Optimum Interpolation Weights for Hybrid Autoregressive Transducer Mannequin

Ehsan Variani, Michael Riley, David Rybach, Cyril Allauzen, Tongzhou Chen, Bhuvana Ramabhadran

Streaming Align-Refine for Non-autoregressive Deliberation

Wang Weiran, Ke Hu, Tara Sainath

Federated Pruning: Bettering Neural Community Effectivity with Federated Studying


Rongmei Lin^*, Yonghui Xiao, Tien-Ju Yang, Ding Zhao, Li Xiong, Giovanni Motta, Françoise Beaufays

A Unified Cascaded Encoder ASR Mannequin for Dynamic Mannequin Sizes

Shaojin Ding, Weiran Wang, Ding Zhao, Tara N Sainath, Yanzhang He, Robert David, Rami Botros, Xin Wang, Rina Panigrahy, Qiao Liang, Dongseong Hwang, Ian McGraw, Rohit Prabhavalkar, Trevor Strohman

4-Bit Conformer with Native Quantization Conscious Coaching for Speech Recognition

Shaojin Ding, Phoenix Meadowlark, Yanzhang He, Lukasz Lew, Shivani Agrawal, Oleg Rybakov

Visually-Conscious Acoustic Occasion Detection Utilizing Heterogeneous Graphs


Amir Shirian, Krishna Somandepalli, Victor Sanchez, Tanaya Guha

A Conformer-Primarily based Waveform-Area Neural Acoustic Echo Canceller Optimized for ASR Accuracy

Sankaran Panchapagesan, Arun Narayanan, Turaj Zakizadeh Shabestary, Shuai Shao, Nathan Howard, Alex Park, James Walker, Alexander Gruenstein

Lowering Area Mismatch in Self-Supervised Speech Pre-training


Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Yu Zhang, Nicolás Serrano

On-the-Fly ASR Corrections with Audio Exemplars

Golan Pundak, Tsendsuren Munkhdalai, Khe Chai Sim

A Language Agnostic Multilingual Streaming On-Gadget ASR System

Bo Li, Tara Sainath, Ruoming Pang*, Shuo-Yiin Chang, Qiumin Xu, Trevor Strohman, Vince Chen, Qiao Liang, Heguang Liu, Yanzhang He, Parisa Haghani, Sameer Bidichandani

XTREME-S: Evaluating Cross-Lingual Speech Representations

Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson

In direction of Disentangled Speech Representations

Cal Peyser, Ronny Huang, Andrew Rosenberg, Tara Sainath, Michael Picheny, Kyunghyun Cho

Private VAD 2.0: Optimizing Private Voice Exercise Detection for On-Gadget Speech Recognition

Shaojin Ding, Rajeev Rikhye, Qiao Liang, Yanzhang He, Quan Wang, Arun Narayanan, Tom O’Malley, Ian McGraw

A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation

Tom O’Malley, Arun Narayanan, Quan Wang

Coaching Textual content-To-Speech Methods From Artificial Knowledge: A Sensible Strategy For Accent Switch Duties

Lev Finkelstein, Heiga Zen, Norman Casagrande, Chun-an Chan, Ye Jia, Tom Kenter, Alex Petelin, Jonathan Shen*, Vincent Wan, Yu Zhang, Yonghui Wu, Robert Clark

A Scalable Mannequin Specialization Framework for Coaching and Inference Utilizing Submodels and Its Software to Speech Mannequin Personalization

Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro Moreno

Textual content-Pushed Separation of Arbitrary Sounds

Kevin Kilgour, Beat Gfeller, Qingqing Huang, Aren Jansen, Scott Knowledge, Marco Tagliasacchi

Workshops, Tutorials & Particular Periods

The VoxCeleb Speaker Recognition Problem 2022 (VoxSRC-22)

Organizers embrace: Arsha Nagrani

Self-Supervised Illustration Studying for Speech Processing

Organizers embrace: Tara Sainath

Studying from Weak Labels

Organizers embrace: Ankit Shah

RNN Transducers for Named Entity Recognition with Constraints on Alignment for Understanding Medical Conversations

Authors: Hagen Soltau, Izhak Shafran, Mingqiu Wang, Laurent El Shafey

Listening with Googlears: Low-Latency Neural Multiframe Beamforming and Equalization for Listening to Aids

Authors: Samuel Yang, Scott Knowledge, Chet Gnegy, Richard F. Lyon, Sagar Savla

Utilizing Rater and System Metadata to Clarify Variance within the VoiceMOS Problem 2022 Dataset

Authors: Michael Chinen, Jan Skoglund, Chandan Ok. A. Reddy, Alessandro Ragano, Andrew Hines

Incremental Layer-Sensible Self-Supervised Studying for Environment friendly Unsupervised Speech Area Adaptation On Gadget

Authors: Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra, Nikhil Siddhartha, Trevor Strohman, Françoise Beaufays

Reliable Speech Processing

Organizers embrace: Shrikanth Narayanan

---

^*Work carried out whereas at Google.  ^↩