Alert button
Picture for Yashesh Gaur

Yashesh Gaur

Alert button

Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers

Jun 19, 2020
Naoyuki Kanda, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Zhuo Chen, Tianyan Zhou, Takuya Yoshioka

Figure 1 for Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers
Figure 2 for Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers
Figure 3 for Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers
Figure 4 for Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers
Viaarxiv icon

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition

May 28, 2020
Jinyu Li, Yu Wu, Yashesh Gaur, Chengyi Wang, Rui Zhao, Shujie Liu

Figure 1 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
Figure 2 for On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition
Viaarxiv icon

Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR

May 15, 2020
Hirofumi Inaguma, Yashesh Gaur, Liang Lu, Jinyu Li, Yifan Gong

Figure 1 for Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
Figure 2 for Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
Figure 3 for Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
Figure 4 for Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
Viaarxiv icon

Serialized Output Training for End-to-End Overlapped Speech Recognition

Mar 28, 2020
Naoyuki Kanda, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Takuya Yoshioka

Figure 1 for Serialized Output Training for End-to-End Overlapped Speech Recognition
Figure 2 for Serialized Output Training for End-to-End Overlapped Speech Recognition
Figure 3 for Serialized Output Training for End-to-End Overlapped Speech Recognition
Figure 4 for Serialized Output Training for End-to-End Overlapped Speech Recognition
Viaarxiv icon

Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition

Jan 06, 2020
Zhong Meng, Jinyu Li, Yashesh Gaur, Yifan Gong

Figure 1 for Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
Figure 2 for Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
Figure 3 for Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
Viaarxiv icon

Character-Aware Attention-Based End-to-End Speech Recognition

Jan 06, 2020
Zhong Meng, Yashesh Gaur, Jinyu Li, Yifan Gong

Figure 1 for Character-Aware Attention-Based End-to-End Speech Recognition
Figure 2 for Character-Aware Attention-Based End-to-End Speech Recognition
Figure 3 for Character-Aware Attention-Based End-to-End Speech Recognition
Figure 4 for Character-Aware Attention-Based End-to-End Speech Recognition
Viaarxiv icon

Speaker Adaptation for Attention-Based End-to-End Speech Recognition

Nov 09, 2019
Zhong Meng, Yashesh Gaur, Jinyu Li, Yifan Gong

Figure 1 for Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Figure 2 for Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Figure 3 for Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Figure 4 for Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Viaarxiv icon

Robust Speech Recognition Using Generative Adversarial Networks

Nov 05, 2017
Anuroop Sriram, Heewoo Jun, Yashesh Gaur, Sanjeev Satheesh

Figure 1 for Robust Speech Recognition Using Generative Adversarial Networks
Figure 2 for Robust Speech Recognition Using Generative Adversarial Networks
Figure 3 for Robust Speech Recognition Using Generative Adversarial Networks
Figure 4 for Robust Speech Recognition Using Generative Adversarial Networks
Viaarxiv icon

Exploring Neural Transducers for End-to-End Speech Recognition

Jul 24, 2017
Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur, Yi Li, Hairong Liu, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu

Figure 1 for Exploring Neural Transducers for End-to-End Speech Recognition
Figure 2 for Exploring Neural Transducers for End-to-End Speech Recognition
Figure 3 for Exploring Neural Transducers for End-to-End Speech Recognition
Figure 4 for Exploring Neural Transducers for End-to-End Speech Recognition
Viaarxiv icon