Alert button
Picture for Arun Narayanan

Arun Narayanan

Alert button

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

Sep 14, 2022
Tom O'Malley, Arun Narayanan, Quan Wang

Figure 1 for A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation
Figure 2 for A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation
Figure 3 for A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation
Figure 4 for A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation
Viaarxiv icon

Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments

May 17, 2022
Joe Caroselli, Arun Narayanan, Yiteng Huang

Figure 1 for Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments
Figure 2 for Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments
Figure 3 for Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments
Figure 4 for Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments
Viaarxiv icon

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

May 06, 2022
Sankaran Panchapagesan, Arun Narayanan, Turaj Zakizadeh Shabestary, Shuai Shao, Nathan Howard, Alex Park, James Walker, Alexander Gruenstein

Figure 1 for A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Figure 2 for A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Figure 3 for A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Figure 4 for A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Viaarxiv icon

Mask scalar prediction for improving robust automatic speech recognition

Apr 26, 2022
Arun Narayanan, James Walker, Sankaran Panchapagesan, Nathan Howard, Yuma Koizumi

Figure 1 for Mask scalar prediction for improving robust automatic speech recognition
Figure 2 for Mask scalar prediction for improving robust automatic speech recognition
Figure 3 for Mask scalar prediction for improving robust automatic speech recognition
Figure 4 for Mask scalar prediction for improving robust automatic speech recognition
Viaarxiv icon

Extracting Targeted Training Data from ASR Models, and How to Mitigate It

Apr 18, 2022
Ehsan Amid, Om Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays

Figure 1 for Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Figure 2 for Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Figure 3 for Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Figure 4 for Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Viaarxiv icon

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

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

A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation

Nov 18, 2021
Tom O'Malley, Arun Narayanan, Quan Wang, Alex Park, James Walker, Nathan Howard

Figure 1 for A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
Figure 2 for A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
Figure 3 for A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
Figure 4 for A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
Viaarxiv icon

SNRi Target Training for Joint Speech Enhancement and Recognition

Nov 01, 2021
Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani

Figure 1 for SNRi Target Training for Joint Speech Enhancement and Recognition
Figure 2 for SNRi Target Training for Joint Speech Enhancement and Recognition
Figure 3 for SNRi Target Training for Joint Speech Enhancement and Recognition
Figure 4 for SNRi Target Training for Joint Speech Enhancement and Recognition
Viaarxiv icon

Cross-attention conformer for context modeling in speech enhancement for ASR

Oct 30, 2021
Arun Narayanan, Chung-Cheng Chiu, Tom O'Malley, Quan Wang, Yanzhang He

Figure 1 for Cross-attention conformer for context modeling in speech enhancement for ASR
Figure 2 for Cross-attention conformer for context modeling in speech enhancement for ASR
Figure 3 for Cross-attention conformer for context modeling in speech enhancement for ASR
Figure 4 for Cross-attention conformer for context modeling in speech enhancement for ASR
Viaarxiv icon

Personalized Keyphrase Detection using Speaker and Environment Information

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