Alert button
Picture for Suwon Shon

Suwon Shon

Alert button

Improving ASR Contextual Biasing with Guided Attention

Jan 16, 2024
Jiyang Tang, Kwangyoun Kim, Suwon Shon, Felix Wu, Prashant Sridhar, Shinji Watanabe

Viaarxiv icon

Generative Context-aware Fine-tuning of Self-supervised Speech Models

Dec 15, 2023
Suwon Shon, Kwangyoun Kim, Prashant Sridhar, Yi-Te Hsu, Shinji Watanabe, Karen Livescu

Viaarxiv icon

A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks

May 18, 2023
Yifan Peng, Kwangyoun Kim, Felix Wu, Brian Yan, Siddhant Arora, William Chen, Jiyang Tang, Suwon Shon, Prashant Sridhar, Shinji Watanabe

Figure 1 for A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks
Figure 2 for A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks
Figure 3 for A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks
Figure 4 for A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks
Viaarxiv icon

SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks

Dec 20, 2022
Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin, Ankita Pasad, Felix Wu, Roshan Sharma, Wei-Lun Wu, Hung-Yi Lee, Karen Livescu, Shinji Watanabe

Figure 1 for SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
Figure 2 for SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
Figure 3 for SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
Figure 4 for SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
Viaarxiv icon

Context-aware Fine-tuning of Self-supervised Speech Models

Dec 16, 2022
Suwon Shon, Felix Wu, Kwangyoun Kim, Prashant Sridhar, Karen Livescu, Shinji Watanabe

Figure 1 for Context-aware Fine-tuning of Self-supervised Speech Models
Figure 2 for Context-aware Fine-tuning of Self-supervised Speech Models
Figure 3 for Context-aware Fine-tuning of Self-supervised Speech Models
Figure 4 for Context-aware Fine-tuning of Self-supervised Speech Models
Viaarxiv icon

On the Use of External Data for Spoken Named Entity Recognition

Dec 14, 2021
Ankita Pasad, Felix Wu, Suwon Shon, Karen Livescu, Kyu J. Han

Figure 1 for On the Use of External Data for Spoken Named Entity Recognition
Figure 2 for On the Use of External Data for Spoken Named Entity Recognition
Figure 3 for On the Use of External Data for Spoken Named Entity Recognition
Figure 4 for On the Use of External Data for Spoken Named Entity Recognition
Viaarxiv icon

SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech

Nov 19, 2021
Suwon Shon, Ankita Pasad, Felix Wu, Pablo Brusco, Yoav Artzi, Karen Livescu, Kyu J. Han

Figure 1 for SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech
Figure 2 for SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech
Figure 3 for SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech
Figure 4 for SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech
Viaarxiv icon

Leveraging Pre-trained Language Model for Speech Sentiment Analysis

Jun 11, 2021
Suwon Shon, Pablo Brusco, Jing Pan, Kyu J. Han, Shinji Watanabe

Figure 1 for Leveraging Pre-trained Language Model for Speech Sentiment Analysis
Figure 2 for Leveraging Pre-trained Language Model for Speech Sentiment Analysis
Figure 3 for Leveraging Pre-trained Language Model for Speech Sentiment Analysis
Figure 4 for Leveraging Pre-trained Language Model for Speech Sentiment Analysis
Viaarxiv icon

Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification

May 11, 2019
Achintya kr. Sarkar, Zheng-Hua Tan, Hao Tang, Suwon Shon, James Glass

Figure 1 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 2 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 3 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Figure 4 for Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
Viaarxiv icon

Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain

Dec 04, 2018
Suwon Shon, Ahmed Ali, James Glass

Figure 1 for Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain
Figure 2 for Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain
Figure 3 for Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain
Figure 4 for Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain
Viaarxiv icon