Paper ID | SPE-22.5 | ||
Paper Title | DECOUPLING PRONUNCIATION AND LANGUAGE FOR END-TO-END CODE-SWITCHING AUTOMATIC SPEECH RECOGNITION | ||
Authors | Shuai Zhang, School of Artificial Intelligence, University of Chinese Academy of Sciences, China; Jiangyan Yi, Institute of Automation, Chinese Academy of Sciences, China; Zhengkun Tian, Ye Bai, Jianhua Tao, Zhengqi Wen, School of Artificial Intelligence, University of Chinese Academy of Sciences, China | ||
Session | SPE-22: Speech Recognition 8: Multilingual Speech Recognition | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
Presentation Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-MULT] Multilingual Recognition and Identification | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models' performance. In this paper, we propose a decoupled transformer model to use monolingual paired data and unpaired text data to alleviate the problem of code-switching data shortage. The model is decoupled into two parts: audio-to-phoneme (A2P) network and phoneme-to-text (P2T) network. The A2P network can learn acoustic pattern scenarios using large-scale monolingual paired data. Meanwhile, it generates multiple phoneme sequence candidates for single audio data in real time during the training process. Then the generated phoneme-text paired data is used to train the P2T network. This network can be pre-trained with large amounts of external unpaired text data. By using monolingual data and unpaired text data, the decoupled transformer model reduces the high dependency on code-switching paired training data of E2E model to a certain extent. Finally, the two networks are optimized jointly through attention fusion. We evaluate the proposed method on the public Mandarin-English code-switching dataset. Compared with our transformer baseline, the proposed method achieves 18.14\% relative mix error rate reduction. |