An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging Encoder Disentanglement
This addresses the problem of degraded ASR performance in multilingual or code-switching scenarios, which is incremental as it builds on existing encoder-based approaches.
The paper tackles the challenge of code-switching in automatic speech recognition by improving the acoustic encoder with a disentanglement loss and mixture-of-experts architecture, achieving better performance than prior methods while using half the parameters.
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 main contributions are threefold: First, we introduce a novel disentanglement loss to enable the lower-layer of the encoder to capture inter-lingual acoustic information while mitigating linguistic confusion at the higher-layer of the encoder. Second, through comprehensive experiments, we verify that our proposed method outperforms the prior-art methods using pretrained dual-encoders, meanwhile having access only to the codeswitching corpus and consuming half of the parameterization. Third, the apparent differentiation of the encoders' output features also corroborates the complementarity between the disentanglement loss and the mixture-of-experts (MoE) architecture.