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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for James Glass

James Glass

SSAST: Self-Supervised Audio Spectrogram Transformer


Oct 19, 2021
Yuan Gong, Cheng-I Jeff Lai, Yu-An Chung, James Glass

Figure 1 for SSAST: Self-Supervised Audio Spectrogram Transformer
Figure 2 for SSAST: Self-Supervised Audio Spectrogram Transformer
Figure 3 for SSAST: Self-Supervised Audio Spectrogram Transformer
Figure 4 for SSAST: Self-Supervised Audio Spectrogram Transformer

  Access Paper or Ask Questions

Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset


Oct 14, 2021
Ian Palmer, Andrew Rouditchenko, Andrei Barbu, Boris Katz, James Glass

Figure 1 for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset
Figure 2 for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset
Figure 3 for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset
Figure 4 for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset
* Presented at Interspeech 2021. This version contains additional experiments on the Spoken ObjectNet test set 
  Access Paper or Ask Questions

Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0


Oct 07, 2021
Sameer Khurana, Antoine Laurent, James Glass

Figure 1 for Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
Figure 2 for Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
Figure 3 for Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0

  Access Paper or Ask Questions

On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis


Oct 04, 2021
Cheng-I Jeff Lai, Erica Cooper, Yang Zhang, Shiyu Chang, Kaizhi Qian, Yi-Lun Liao, Yung-Sung Chuang, Alexander H. Liu, Junichi Yamagishi, David Cox, James Glass

Figure 1 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 2 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 3 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Figure 4 for On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis

  Access Paper or Ask Questions

An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models


Sep 11, 2021
Tianxing He, Kyunghyun Cho, James Glass

Figure 1 for An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Figure 2 for An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Figure 3 for An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Figure 4 for An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models

  Access Paper or Ask Questions

Interpretable Propaganda Detection in News Articles


Aug 29, 2021
Seunghak Yu, Giovanni Da San Martino, Mitra Mohtarami, James Glass, Preslav Nakov

Figure 1 for Interpretable Propaganda Detection in News Articles
Figure 2 for Interpretable Propaganda Detection in News Articles
Figure 3 for Interpretable Propaganda Detection in News Articles
Figure 4 for Interpretable Propaganda Detection in News Articles
* RANLP-2021 
 * propaganda, propaganda techniques, disinformation, misinformation, fake news, explainability, interpretability 
  Access Paper or Ask Questions

Mitigating Biases in Toxic Language Detection through Invariant Rationalization


Jun 14, 2021
Yung-Sung Chuang, Mingye Gao, Hongyin Luo, James Glass, Hung-yi Lee, Yun-Nung Chen, Shang-Wen Li

Figure 1 for Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Figure 2 for Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Figure 3 for Mitigating Biases in Toxic Language Detection through Invariant Rationalization
* The 5th Workshop on Online Abuse and Harms at ACL 2021 
  Access Paper or Ask Questions

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition


Jun 10, 2021
Cheng-I Jeff Lai, Yang Zhang, Alexander H. Liu, Shiyu Chang, Yi-Lun Liao, Yung-Sung Chuang, Kaizhi Qian, Sameer Khurana, David Cox, James Glass

Figure 1 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 2 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 3 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Figure 4 for PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

  Access Paper or Ask Questions

Cross-Modal Discrete Representation Learning


Jun 10, 2021
Alexander H. Liu, SouYoung Jin, Cheng-I Jeff Lai, Andrew Rouditchenko, Aude Oliva, James Glass

Figure 1 for Cross-Modal Discrete Representation Learning
Figure 2 for Cross-Modal Discrete Representation Learning
Figure 3 for Cross-Modal Discrete Representation Learning
Figure 4 for Cross-Modal Discrete Representation Learning
* Preprint 
  Access Paper or Ask Questions

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions


May 10, 2021
Mathew Monfort, SouYoung Jin, Alexander Liu, David Harwath, Rogerio Feris, James Glass, Aude Oliva

Figure 1 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 2 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 3 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 4 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
* To appear at CVPR 2021 
  Access Paper or Ask Questions

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos


May 05, 2021
Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Michael Picheny, Shih-Fu Chang

Figure 1 for Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
Figure 2 for Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
Figure 3 for Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
Figure 4 for Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos

  Access Paper or Ask Questions

AST: Audio Spectrogram Transformer


Apr 06, 2021
Yuan Gong, Yu-An Chung, James Glass

Figure 1 for AST: Audio Spectrogram Transformer
Figure 2 for AST: Audio Spectrogram Transformer
Figure 3 for AST: Audio Spectrogram Transformer
Figure 4 for AST: Audio Spectrogram Transformer

  Access Paper or Ask Questions

Cooperative Learning of Zero-Shot Machine Reading Comprehension


Mar 22, 2021
Hongyin Luo, Shang-Wen Li, Seunghak Yu, James Glass

Figure 1 for Cooperative Learning of Zero-Shot Machine Reading Comprehension
Figure 2 for Cooperative Learning of Zero-Shot Machine Reading Comprehension
Figure 3 for Cooperative Learning of Zero-Shot Machine Reading Comprehension
Figure 4 for Cooperative Learning of Zero-Shot Machine Reading Comprehension

  Access Paper or Ask Questions

PSLA: Improving Audio Event Classification with Pretraining, Sampling, Labeling, and Aggregation


Feb 02, 2021
Yuan Gong, Yu-An Chung, James Glass

Figure 1 for PSLA: Improving Audio Event Classification with Pretraining, Sampling, Labeling, and Aggregation
Figure 2 for PSLA: Improving Audio Event Classification with Pretraining, Sampling, Labeling, and Aggregation
Figure 3 for PSLA: Improving Audio Event Classification with Pretraining, Sampling, Labeling, and Aggregation
Figure 4 for PSLA: Improving Audio Event Classification with Pretraining, Sampling, Labeling, and Aggregation

  Access Paper or Ask Questions

Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks


Jan 24, 2021
Hongyin Luo, Shang-Wen Li, James Glass

Figure 1 for Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks
Figure 2 for Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks
Figure 3 for Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks
Figure 4 for Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks
* Appears in the Proceedings of the 3rd Clinical Natural Language Processing Workshop 
  Access Paper or Ask Questions

Text-Free Image-to-Speech Synthesis Using Learned Segmental Units


Dec 31, 2020
Wei-Ning Hsu, David Harwath, Christopher Song, James Glass

Figure 1 for Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
Figure 2 for Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
Figure 3 for Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
Figure 4 for Text-Free Image-to-Speech Synthesis Using Learned Segmental Units

  Access Paper or Ask Questions

Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies


Nov 01, 2020
Alexander H. Liu, Yu-An Chung, James Glass

Figure 1 for Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
Figure 2 for Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
Figure 3 for Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
Figure 4 for Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies
* Preprint 
  Access Paper or Ask Questions

Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining


Oct 26, 2020
Cheng-I Lai, Yung-Sung Chuang, Hung-Yi Lee, Shang-Wen Li, James Glass

Figure 1 for Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining
Figure 2 for Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining
Figure 3 for Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining
Figure 4 for Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining

  Access Paper or Ask Questions

Similarity Analysis of Self-Supervised Speech Representations


Oct 22, 2020
Yu-An Chung, Yonatan Belinkov, James Glass

Figure 1 for Similarity Analysis of Self-Supervised Speech Representations
Figure 2 for Similarity Analysis of Self-Supervised Speech Representations
Figure 3 for Similarity Analysis of Self-Supervised Speech Representations
Figure 4 for Similarity Analysis of Self-Supervised Speech Representations

  Access Paper or Ask Questions

We Can Detect Your Bias: Predicting the Political Ideology of News Articles


Oct 11, 2020
Ramy Baly, Giovanni Da San Martino, James Glass, Preslav Nakov

Figure 1 for We Can Detect Your Bias: Predicting the Political Ideology of News Articles
Figure 2 for We Can Detect Your Bias: Predicting the Political Ideology of News Articles
Figure 3 for We Can Detect Your Bias: Predicting the Political Ideology of News Articles
Figure 4 for We Can Detect Your Bias: Predicting the Political Ideology of News Articles
* EMNLP-2020 
 * Political bias, bias in news, neural networks bias, adversarial adaptation, triplet loss, transformers, recurrent neural networks 
  Access Paper or Ask Questions

A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation


Sep 15, 2020
Moin Nadeem, Tianxing He, Kyunghyun Cho, James Glass

Figure 1 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 2 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 3 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 4 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
* To appear at AACL 2020; 9 pages, 12 figures, 2 tables 
  Access Paper or Ask Questions

Constructing a Knowledge Graph from Unstructured Documents without External Alignment


Aug 20, 2020
Seunghak Yu, Tianxing He, James Glass

Figure 1 for Constructing a Knowledge Graph from Unstructured Documents without External Alignment
Figure 2 for Constructing a Knowledge Graph from Unstructured Documents without External Alignment
Figure 3 for Constructing a Knowledge Graph from Unstructured Documents without External Alignment
Figure 4 for Constructing a Knowledge Graph from Unstructured Documents without External Alignment

  Access Paper or Ask Questions

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos


Jun 16, 2020
Andrew Rouditchenko, Angie Boggust, David Harwath, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Rogerio Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James Glass

Figure 1 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 2 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 3 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Figure 4 for AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

  Access Paper or Ask Questions

CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning


Jun 04, 2020
Sameer Khurana, Antoine Laurent, James Glass

Figure 1 for CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
Figure 2 for CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
Figure 3 for CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
Figure 4 for CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
* submitted to INTERSPEECH 
  Access Paper or Ask Questions

A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning


Jun 03, 2020
Sameer Khurana, Antoine Laurent, Wei-Ning Hsu, Jan Chorowski, Adrian Lancucki, Ricard Marxer, James Glass

Figure 1 for A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
Figure 2 for A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
Figure 3 for A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
* Submitted to Interspeech 2020 
  Access Paper or Ask Questions

Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption


May 19, 2020
Hongyin Luo, Shang-Wen Li, James Glass

Figure 1 for Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
Figure 2 for Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
Figure 3 for Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
Figure 4 for Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption

  Access Paper or Ask Questions