An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement

arXiv:2402.17189v1 Announce Type: new
Abstract: With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders ASR from perfection, as the lack of labeled data and the variations between languages often lead to degradation of ASR performance. In this paper, we focus exclusively on improving the acoustic encoder of E2E ASR to tackle the challenge caused by the codeswitching phenomenon. Our …

abstract arxiv asr automatic speech recognition code cs.ai cs.cl cs.sd data e2e eess.as encoder experts languages major massive networks neural networks recognition speech speech recognition type