4 papers
Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection
Tzu-Ting Yang, Hsin-Wei Wang, Yi-Cheng Wang +1
Code-switching-where multilingual speakers alternately switch between languages during conversations-still poses significant challenges to end-to-end (E2E) automatic speech recogni…
An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement
Tzu-Ting Yang, Hsin-Wei Wang, Yi-Cheng Wang +2
With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codes…
Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition
Tzu-Ting Yang, Hsin-Wei Wang, Berlin Chen
In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional…
AVATAR: Robust Voice Search Engine Leveraging Autoregressive Document Retrieval and Contrastive Learning
Yi-Cheng Wang, Tzu-Ting Yang, Hsin-Wei Wang +2
Voice, as input, has progressively become popular on mobiles and seems to transcend almost entirely text input. Through voice, the voice search (VS) system can provide a more natur…