Picture for Linquan Liu

Linquan Liu

WavLLM: Towards Robust and Adaptive Speech Large Language Model

Add code
Mar 31, 2024
Figure 1 for WavLLM: Towards Robust and Adaptive Speech Large Language Model
Figure 2 for WavLLM: Towards Robust and Adaptive Speech Large Language Model
Figure 3 for WavLLM: Towards Robust and Adaptive Speech Large Language Model
Figure 4 for WavLLM: Towards Robust and Adaptive Speech Large Language Model
Viaarxiv icon

On decoder-only architecture for speech-to-text and large language model integration

Add code
Jul 14, 2023
Figure 1 for On decoder-only architecture for speech-to-text and large language model integration
Figure 2 for On decoder-only architecture for speech-to-text and large language model integration
Figure 3 for On decoder-only architecture for speech-to-text and large language model integration
Viaarxiv icon

Code-Switching Text Generation and Injection in Mandarin-English ASR

Add code
Mar 20, 2023
Figure 1 for Code-Switching Text Generation and Injection in Mandarin-English ASR
Figure 2 for Code-Switching Text Generation and Injection in Mandarin-English ASR
Figure 3 for Code-Switching Text Generation and Injection in Mandarin-English ASR
Figure 4 for Code-Switching Text Generation and Injection in Mandarin-English ASR
Viaarxiv icon

FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model

Add code
Mar 08, 2023
Figure 1 for FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
Figure 2 for FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
Figure 3 for FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
Figure 4 for FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
Viaarxiv icon

Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training

Add code
Mar 01, 2023
Figure 1 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 2 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 3 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Figure 4 for Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training
Viaarxiv icon

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

Add code
Jan 04, 2022
Figure 1 for Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
Figure 2 for Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
Figure 3 for Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
Figure 4 for Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition
Viaarxiv icon

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition

Add code
Oct 18, 2021
Figure 1 for FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Figure 2 for FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Figure 3 for FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Figure 4 for FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Viaarxiv icon

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

Add code
Jun 03, 2021
Figure 1 for FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Figure 2 for FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Figure 3 for FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Figure 4 for FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Viaarxiv icon