Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Mu Yang

Mu Yang

Learning ASR pathways: A sparse multilingual ASR model

Sep 13, 2022
Mu Yang, Andros Tjandra, Chunxi Liu, David Zhang, Duc Le, John H. L. Hansen, Ozlem Kalinli

Figure 1 for Learning ASR pathways: A sparse multilingual ASR model

Figure 2 for Learning ASR pathways: A sparse multilingual ASR model

Figure 3 for Learning ASR pathways: A sparse multilingual ASR model

Figure 4 for Learning ASR pathways: A sparse multilingual ASR model

* 5 pages, 3 figures

Access Paper or Ask Questions

Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment

Apr 07, 2022
Mu Yang, Kevin Hirschi, Stephen D. Looney, Okim Kang, John H. L. Hansen

Figure 1 for Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment

Figure 2 for Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment

Figure 3 for Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment

Figure 4 for Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment

* Submitted to Interspeech 2022

Access Paper or Ask Questions

InverseMV: Composing Piano Scores with a Convolutional Video-Music Transformer

Dec 31, 2021
Chin-Tung Lin, Mu Yang

Figure 1 for InverseMV: Composing Piano Scores with a Convolutional Video-Music Transformer

Figure 2 for InverseMV: Composing Piano Scores with a Convolutional Video-Music Transformer

Figure 3 for InverseMV: Composing Piano Scores with a Convolutional Video-Music Transformer

Figure 4 for InverseMV: Composing Piano Scores with a Convolutional Video-Music Transformer

* Rejected by ISMIR 2020

Access Paper or Ask Questions

Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

Oct 09, 2021
Mu Yang, Shaojin Ding, Tianlong Chen, Tong Wang, Zhangyang Wang

Figure 1 for Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

Figure 2 for Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

Figure 3 for Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

Figure 4 for Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

* Submitted to ICASSP 2022

Access Paper or Ask Questions

Biomedical Event Extraction with Hierarchical Knowledge Graphs

Oct 12, 2020
Kung-Hsiang Huang, Mu Yang, Nanyun Peng

Figure 1 for Biomedical Event Extraction with Hierarchical Knowledge Graphs

Figure 2 for Biomedical Event Extraction with Hierarchical Knowledge Graphs

Figure 3 for Biomedical Event Extraction with Hierarchical Knowledge Graphs

Figure 4 for Biomedical Event Extraction with Hierarchical Knowledge Graphs

* 8 pages, 3 figures, Findings of EMNLP 2020 (short)

Access Paper or Ask Questions

Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

Sep 22, 2020
Kung-Hsiang Huang, Mu Yang, Nanyun Peng

Figure 1 for Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

Figure 2 for Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

Figure 3 for Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

Figure 4 for Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

* 8 pages, 3 figures, Findings of EMNLP 2020 (short)

Access Paper or Ask Questions

Deep Structured Neural Network for Event Temporal Relation Extraction

Sep 24, 2019
Rujun Han, I-Hung Hsu, Mu Yang, Aram Galstyan, Ralph Weischedel, Nanyun Peng

Figure 1 for Deep Structured Neural Network for Event Temporal Relation Extraction

Figure 2 for Deep Structured Neural Network for Event Temporal Relation Extraction

Figure 3 for Deep Structured Neural Network for Event Temporal Relation Extraction

Figure 4 for Deep Structured Neural Network for Event Temporal Relation Extraction

* This paper will be published in CoNLL 2019

Access Paper or Ask Questions