Alert button
Picture for Chunyang Wu

Chunyang Wu

Alert button

Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data

Add code
Bookmark button
Alert button
Nov 12, 2023
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

Viaarxiv icon

Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model

Add code
Bookmark button
Alert button
Sep 22, 2023
Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli

Figure 1 for Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Figure 2 for Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Figure 3 for Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Figure 4 for Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Viaarxiv icon

End-to-End Speech Recognition Contextualization with Large Language Models

Add code
Bookmark button
Alert button
Sep 19, 2023
Egor Lakomkin, Chunyang Wu, Yassir Fathullah, Ozlem Kalinli, Michael L. Seltzer, Christian Fuegen

Figure 1 for End-to-End Speech Recognition Contextualization with Large Language Models
Figure 2 for End-to-End Speech Recognition Contextualization with Large Language Models
Figure 3 for End-to-End Speech Recognition Contextualization with Large Language Models
Figure 4 for End-to-End Speech Recognition Contextualization with Large Language Models
Viaarxiv icon

TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models

Add code
Bookmark button
Alert button
Sep 05, 2023
Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra

Figure 1 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 2 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 3 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Figure 4 for TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Viaarxiv icon

Prompting Large Language Models with Speech Recognition Abilities

Add code
Bookmark button
Alert button
Jul 21, 2023
Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer

Figure 1 for Prompting Large Language Models with Speech Recognition Abilities
Figure 2 for Prompting Large Language Models with Speech Recognition Abilities
Figure 3 for Prompting Large Language Models with Speech Recognition Abilities
Figure 4 for Prompting Large Language Models with Speech Recognition Abilities
Viaarxiv icon

Towards Selection of Text-to-speech Data to Augment ASR Training

Add code
Bookmark button
Alert button
May 30, 2023
Shuo Liu, Leda Sarı, Chunyang Wu, Gil Keren, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli

Figure 1 for Towards Selection of Text-to-speech Data to Augment ASR Training
Figure 2 for Towards Selection of Text-to-speech Data to Augment ASR Training
Figure 3 for Towards Selection of Text-to-speech Data to Augment ASR Training
Figure 4 for Towards Selection of Text-to-speech Data to Augment ASR Training
Viaarxiv icon

Multi-Head State Space Model for Speech Recognition

Add code
Bookmark button
Alert button
May 25, 2023
Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales

Figure 1 for Multi-Head State Space Model for Speech Recognition
Figure 2 for Multi-Head State Space Model for Speech Recognition
Figure 3 for Multi-Head State Space Model for Speech Recognition
Figure 4 for Multi-Head State Space Model for Speech Recognition
Viaarxiv icon

Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution

Add code
Bookmark button
Alert button
Oct 07, 2021
Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer

Figure 1 for Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Figure 2 for Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Figure 3 for Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Figure 4 for Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Viaarxiv icon

Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios

Add code
Bookmark button
Alert button
Apr 06, 2021
Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer

Figure 1 for Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
Figure 2 for Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
Figure 3 for Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
Figure 4 for Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
Viaarxiv icon