Picture for Nana Hou

Nana Hou

Self-critical Sequence Training for Automatic Speech Recognition

Apr 13, 2022
Figure 1 for Self-critical Sequence Training for Automatic Speech Recognition
Figure 2 for Self-critical Sequence Training for Automatic Speech Recognition
Figure 3 for Self-critical Sequence Training for Automatic Speech Recognition
Figure 4 for Self-critical Sequence Training for Automatic Speech Recognition
Viaarxiv icon

Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning

Apr 12, 2022
Figure 1 for Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Figure 2 for Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Figure 3 for Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Figure 4 for Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Viaarxiv icon

Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting

Add code
Mar 30, 2022
Figure 1 for Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
Figure 2 for Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
Figure 3 for Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
Figure 4 for Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
Viaarxiv icon

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

Add code
Mar 29, 2022
Figure 1 for Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
Figure 2 for Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
Figure 3 for Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
Figure 4 for Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
Viaarxiv icon

Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition

Add code
Mar 28, 2022
Figure 1 for Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
Figure 2 for Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
Figure 3 for Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
Figure 4 for Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
Viaarxiv icon

Progressive Continual Learning for Spoken Keyword Spotting

Feb 07, 2022
Figure 1 for Progressive Continual Learning for Spoken Keyword Spotting
Figure 2 for Progressive Continual Learning for Spoken Keyword Spotting
Figure 3 for Progressive Continual Learning for Spoken Keyword Spotting
Figure 4 for Progressive Continual Learning for Spoken Keyword Spotting
Viaarxiv icon

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

Add code
Oct 11, 2021
Figure 1 for Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
Figure 2 for Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
Figure 3 for Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
Figure 4 for Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
Viaarxiv icon

Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech

Add code
Jul 22, 2021
Figure 1 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 2 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 3 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 4 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Viaarxiv icon