Towards End-to-End Code-Switching Speech Recognition
This addresses the problem of eliminating expert linguistic knowledge for researchers in multilingual speech recognition, but it is incremental as it builds on existing end-to-end methods.
The paper tackles code-switching speech recognition by developing a hybrid CTC-Attention end-to-end system for Mandarin-English, achieving a mixed error rate of 34.24% on the SEAME corpus.
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic speech recognition (ASR) simplifies the building of ASR systems considerably by predicting graphemes or characters directly from acoustic input. In the mean time, the need of expert linguistic knowledge is also eliminated, which makes it an attractive choice for code-switching ASR. This paper presents a hybrid CTC-Attention based end-to-end Mandarin-English code-switching (CS) speech recognition system and studies the effect of hybrid CTC-Attention based models, different modeling units, the inclusion of language identification and different decoding strategies on the task of code-switching ASR. On the SEAME corpus, our system achieves a mixed error rate (MER) of 34.24%.