Picture for Yexin Yang

Yexin Yang

CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Add code
Jul 09, 2024
Viaarxiv icon

SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability

Add code
Aug 16, 2023
Viaarxiv icon

AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge

Add code
Feb 19, 2021
Figure 1 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 2 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 3 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 4 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Viaarxiv icon