paper-with-me

Papers

Reducing language context confusion for end-to-end code-switching automatic speech recognition

2022-01-28 · Shuai Zhang, Jiangyan Yi, Zhengkun Tian, JianHua Tao, Yu Ting Yeung, Liqun Deng

Code-switching deals with alternative languages in communication process. Training end-to-end (E2E) automatic speech recognition (ASR) systems for code-switching is especially challenging as code-switching training data are always insufficient to combat the increased multilingual context confusion due to the presence of more than one language. We propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint (EC) Theory. The linguistic theory requires that any monolingual fragment that occurs in the code-switching sentence must occur in one of the monolingual sentences. The theory establishes a bridge between monolingual data and code-switching data. We leverage this linguistics theory to design the code-switching E2E ASR model. The proposed model efficiently transfers language knowledge from rich monolingual data to improve the performance of the code-switching ASR model. We evaluate our model on ASRU 2019 Mandarin-English code-switching challenge dataset. Compared to the baseline model, our proposed model achieves a 17.12% relative error reduction.

📄 PDF Abstract BibTeX arXiv:2201.12155

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

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

2022-10-26 · Hexin Liu, HaiHua Xu, Leibny Paola Garcia, Andy W. H. Khong 외

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improvin…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition

2023-12-15 · Tzu-Ting Yang, Hsin-Wei Wang, Berlin Chen

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It i…

Automatic Speech RecognitionLanguage IdentificationLanguage ModelingLanguage Modelling+2

Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation

2025-10-20 · Collin Zhang, Fei Huang, Chenhan Yuan, Junyang Lin arxiv

Large language models (LLMs) often experience language confusion, which is the unintended mixing of languages during text generation. Current solutions to this problem either necessitate model retraining or cannot differ…

Text Generation

Aligning Speech to Languages to Enhance Code-switching Speech Recognition

2024-03-09 · Hexin Liu, Xiangyu Zhang, Haoyang Zhang, Leibny Paola Garcia 외

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we introduce a novel language align…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Identification+4

Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning

2026-06-08 · Trapoom Ukarapol, Pakhapoom Sarapat, Nut Chukamphaeng arxiv

Large language models (LLMs) sometimes exhibit language confusion when generating non-English text. Existing approaches typically rely on fine-tuning to mitigate this issue. In contrast, we propose a tuning-free paradigm…