| Paper ID | SPE-22.3 |
| Paper Title |
REDUCING SPELLING INCONSISTENCIES IN CODE-SWITCHING ASR USING CONTEXTUALIZED CTC LOSS |
| Authors |
Burin Naowarat, Thananchai Kongthaworn, Chulalongkorn University, Thailand; Korrawe Karunratanakul, ETH Zurich, Switzerland; Sheng Hui Wu, NewEra AI Robotics, Taiwan; Ekapol Chuangsuwanich, Chulalongkorn University, Thailand |
| 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 |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models. With the combined choice of characters from multiple languages, the outcome from character-based models suffers from phoneme duplication, resulting in language-inconsistent spellings. We propose Contextualized Connectionist Temporal Classification (CCTC) loss to encourage spelling consistencies of a character-based non-autoregressive ASR which allows for faster inference. The model trained by CCTC loss is aware of contexts since it learns to predict both center and surrounding letters in a multi-task manner. In contrast to existing CTC-based approaches, CCTC loss does not require frame-level alignments, since the context ground truth is obtained from the model's estimated path. Compared to the same model trained with regular CTC loss, our method consistently improved the ASR performance on both CS and monolingual corpora. |
