Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss

by   Burin Naowarat, et al.
Chulalongkorn University

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 CCTC loss conditions the main prediction on the predicted contexts to ensure language consistency in the spellings. 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.


page 1

page 2

page 3

page 4


Code-Switching Detection with Data-Augmented Acoustic and Language Models

In this paper, we investigate the code-switching detection performance o...

Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech

In this paper, we describe several techniques for improving the acoustic...

Code-Switching Detection Using ASR-Generated Language Posteriors

Code-switching (CS) detection refers to the automatic detection of langu...

Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Code-switching (CS) refers to the phenomenon that languages switch withi...

Multi-Graph Decoding for Code-Switching ASR

In the FAME! Project, a code-switching (CS) automatic speech recognition...

Distilling the Knowledge of BERT for CTC-based ASR

Connectionist temporal classification (CTC) -based models are attractive...

Multi-sequence Intermediate Conditioning for CTC-based ASR

End-to-end automatic speech recognition (ASR) directly maps input speech...

Please sign up or login with your details

Forgot password? Click here to reset