Alert button
Picture for Weiyi Zheng

Weiyi Zheng

Alert button

Federated Domain Adaptation for ASR with Full Self-Supervision

Apr 05, 2022
Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide

Figure 1 for Federated Domain Adaptation for ASR with Full Self-Supervision
Figure 2 for Federated Domain Adaptation for ASR with Full Self-Supervision
Figure 3 for Federated Domain Adaptation for ASR with Full Self-Supervision
Figure 4 for Federated Domain Adaptation for ASR with Full Self-Supervision
Viaarxiv icon

Scaling ASR Improves Zero and Few Shot Learning

Nov 29, 2021
Alex Xiao, Weiyi Zheng, Gil Keren, Duc Le, Frank Zhang, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Abdelrahman Mohamed

Figure 1 for Scaling ASR Improves Zero and Few Shot Learning
Figure 2 for Scaling ASR Improves Zero and Few Shot Learning
Figure 3 for Scaling ASR Improves Zero and Few Shot Learning
Figure 4 for Scaling ASR Improves Zero and Few Shot Learning
Viaarxiv icon

Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric

Oct 11, 2021
Suyoun Kim, Duc Le, Weiyi Zheng, Tarun Singh, Abhinav Arora, Xiaoyu Zhai, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer

Figure 1 for Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Figure 2 for Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Figure 3 for Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Figure 4 for Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
Viaarxiv icon

Libri-Light: A Benchmark for ASR with Limited or No Supervision

Dec 17, 2019
Jacob Kahn, Morgane Rivière, Weiyi Zheng, Evgeny Kharitonov, Qiantong Xu, Pierre-Emmanuel Mazaré, Julien Karadayi, Vitaliy Liptchinsky, Ronan Collobert, Christian Fuegen, Tatiana Likhomanenko, Gabriel Synnaeve, Armand Joulin, Abdelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 2 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 3 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 4 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Viaarxiv icon

From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition

Oct 11, 2019
Duc Le, Xiaohui Zhang, Weiyi Zheng, Christian Fügen, Geoffrey Zweig, Michael L. Seltzer

Figure 1 for From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Figure 2 for From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Figure 3 for From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Figure 4 for From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Viaarxiv icon