James Glass

UAVM: A Unified Model for Audio-Visual Learning

Jul 29, 2022
Yuan Gong, Alexander H. Liu, Andrew Rouditchenko, James Glass

Figure 2 for UAVM: A Unified Model for Audio-Visual Learning

Figure 3 for UAVM: A Unified Model for Audio-Visual Learning

Figure 4 for UAVM: A Unified Model for Audio-Visual Learning

Developing a Series of AI Challenges for the United States Department of the Air Force

Jul 14, 2022
Vijay Gadepally, Gregory Angelides, Andrei Barbu, Andrew Bowne, Laura J. Brattain, Tamara Broderick, Armando Cabrera, Glenn Carl, Ronisha Carter, Miriam Cha, Emilie Cowen, Jesse Cummings, Bill Freeman, James Glass, Sam Goldberg, Mark Hamilton, Thomas Heldt, Kuan Wei Huang, Phillip Isola, Boris Katz, Jamie Koerner, Yen-Chen Lin, David Mayo, Kyle McAlpin, Taylor Perron, Jean Piou, Hrishikesh M. Rao, Hayley Reynolds, Kaira Samuel, Siddharth Samsi, Morgan Schmidt, Leslie Shing, Olga Simek, Brandon Swenson, Vivienne Sze, Jonathan Taylor, Paul Tylkin, Mark Veillette, Matthew L Weiss, Allan Wollaber, Sophia Yuditskaya, Jeremy Kepner

Figure 2 for Developing a Series of AI Challenges for the United States Department of the Air Force

Figure 3 for Developing a Series of AI Challenges for the United States Department of the Air Force

Figure 4 for Developing a Series of AI Challenges for the United States Department of the Air Force

Access Paper or Ask Questions

SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation

May 17, 2022
Sameer Khurana, Antoine Laurent, James Glass

Figure 2 for SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation

Figure 3 for SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation

Figure 4 for SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation

Access Paper or Ask Questions

Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition

May 06, 2022
Yuan Gong, Jin Yu, James Glass

Figure 2 for Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition

Figure 3 for Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition

Figure 4 for Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition

* Accepted at ICASSP 2022. Dataset and code at https://github.com/YuanGongND/vocalsound Interactive Colab demo at https://colab.research.google.com/github/YuanGongND/vocalsound/blob/main/colab/VocalSound.ipynb

Access Paper or Ask Questions

Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment

May 06, 2022
Yuan Gong, Ziyi Chen, Iek-Heng Chu, Peng Chang, James Glass

Figure 2 for Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment

Figure 3 for Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment

Figure 4 for Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment

* Accepted at ICASSP 2022. Code at https://github.com/YuanGongND/gopt Interactive Colab demo at https://colab.research.google.com/github/YuanGongND/gopt/blob/master/colab/GOPT_GPU.ipynb . ICASSP 2022

Access Paper or Ask Questions

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

Apr 21, 2022
Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljačić, Shang-Wen Li, Wen-tau Yih, Yoon Kim, James Glass

Figure 2 for DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

Figure 3 for DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

Figure 4 for DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

* NAACL 2022 main conference (Long paper). Pretrained models and code are available at https://github.com/voidism/DiffCSE

Access Paper or Ask Questions