Alert button
Picture for Ian McGraw

Ian McGraw

Alert button

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

Add code
Bookmark button
Alert button
Mar 15, 2023
Steven M. Hernandez, Ding Zhao, Shaojin Ding, Antoine Bruguier, Rohit Prabhavalkar, Tara N. Sainath, Yanzhang He, Ian McGraw

Figure 1 for Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Figure 2 for Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Figure 3 for Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Figure 4 for Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
Viaarxiv icon

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

Add code
Bookmark button
Alert button
Apr 20, 2022
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

Figure 1 for A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Figure 2 for A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Figure 3 for A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Figure 4 for A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Viaarxiv icon

Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition

Add code
Bookmark button
Alert button
Apr 13, 2022
Shaojin Ding, Rajeev Rikhye, Qiao Liang, Yanzhang He, Quan Wang, Arun Narayanan, Tom O'Malley, Ian McGraw

Figure 1 for Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Figure 2 for Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Figure 3 for Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Figure 4 for Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Viaarxiv icon

Closing the Gap between Single-User and Multi-User VoiceFilter-Lite

Add code
Bookmark button
Alert button
Feb 24, 2022
Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw

Figure 1 for Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
Figure 2 for Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
Figure 3 for Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
Figure 4 for Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
Viaarxiv icon

Multi-user VoiceFilter-Lite via Attentive Speaker Embedding

Add code
Bookmark button
Alert button
Jul 02, 2021
Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw

Figure 1 for Multi-user VoiceFilter-Lite via Attentive Speaker Embedding
Figure 2 for Multi-user VoiceFilter-Lite via Attentive Speaker Embedding
Figure 3 for Multi-user VoiceFilter-Lite via Attentive Speaker Embedding
Figure 4 for Multi-user VoiceFilter-Lite via Attentive Speaker Embedding
Viaarxiv icon

Personalized Keyphrase Detection using Speaker and Environment Information

Add code
Bookmark button
Alert button
Apr 28, 2021
Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ding Zhao, Yiteng, Huang, Arun Narayanan, Ian McGraw

Figure 1 for Personalized Keyphrase Detection using Speaker and Environment Information
Figure 2 for Personalized Keyphrase Detection using Speaker and Environment Information
Figure 3 for Personalized Keyphrase Detection using Speaker and Environment Information
Figure 4 for Personalized Keyphrase Detection using Speaker and Environment Information
Viaarxiv icon

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction

Add code
Bookmark button
Alert button
Apr 26, 2021
David Qiu, Yanzhang He, Qiujia Li, Yu Zhang, Liangliang Cao, Ian McGraw

Figure 1 for Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
Figure 2 for Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
Figure 3 for Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
Figure 4 for Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
Viaarxiv icon

Learning Word-Level Confidence For Subword End-to-End ASR

Add code
Bookmark button
Alert button
Mar 11, 2021
David Qiu, Qiujia Li, Yanzhang He, Yu Zhang, Bo Li, Liangliang Cao, Rohit Prabhavalkar, Deepti Bhatia, Wei Li, Ke Hu, Tara N. Sainath, Ian McGraw

Figure 1 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 2 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 3 for Learning Word-Level Confidence For Subword End-to-End ASR
Figure 4 for Learning Word-Level Confidence For Subword End-to-End ASR
Viaarxiv icon

Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer

Add code
Bookmark button
Alert button
Jun 02, 2020
Yuan Shangguan, Kate Knister, Yanzhang He, Ian McGraw, Francoise Beaufays

Figure 1 for Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
Figure 2 for Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
Figure 3 for Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
Figure 4 for Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
Viaarxiv icon

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

Add code
Bookmark button
Alert button
Mar 28, 2020
Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier, Shuo-yiin Chang, Wei Li, Raziel Alvarez, Zhifeng Chen, Chung-Cheng Chiu, David Garcia, Alex Gruenstein, Ke Hu, Minho Jin, Anjuli Kannan, Qiao Liang, Ian McGraw, Cal Peyser, Rohit Prabhavalkar, Golan Pundak, David Rybach, Yuan Shangguan, Yash Sheth, Trevor Strohman, Mirko Visontai, Yonghui Wu, Yu Zhang, Ding Zhao

Figure 1 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 2 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 3 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 4 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Viaarxiv icon