Internal Language Model Estimation Based Language Model Fusion For Cross-domain Code-switching Speech Recognition
2022 · Yizhou Peng, Yufei Liu, Jicheng Zhang, et al.
Abstract
Internal Language Model Estimation (ILME) based language model (LM) fusion has been shown significantly improved recognition results over conventional shallow fusion in both intra-domain and cross-domain speech recognition tasks. In this paper, we attempt to apply our ILME method to cross-domain code-switching speech recognition (CSSR) work. Specifically, our curiosity comes from several aspects. First, we are curious about how effective the ILME-based LM fusion is for both intra-domain and cross-domain CSSR tasks. We verify this with or without merging two code-switching domains. More importantly, we train an end-to-end (E2E) speech recognition model by means of merging two monolingual data sets and observe the efficacy of the proposed ILME-based LM fusion for CSSR. Experimental results on SEAME that is from Southeast Asian and another Chinese Mainland CS data set demonstrate the effectiveness of the proposed ILME-based LM fusion method.
Authors
(none)
Tags
Stats
Related papers
- Internal Language Model Estimation Based Adaptive Language Model Fusion For Domain Adaptation (2022)0.00
- Internal Language Model Estimation For Domain-adaptive End-to-end Speech Recognition (2020)13.44
- Internal Language Model Training For Domain-adaptive End-to-end Speech Recognition (2021)11.39
- On The End-to-end Solution To Mandarin-english Code-switching Speech Recognition (2018)12.10
- Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion (2018)0.00
- Delayed Fusion: Integrating Large Language Models Into First-pass Decoding In End-to-end Speech Recognition (2025)5.84
- Integrating Knowledge In End-to-end Automatic Speech Recognition For Mandarin-english Code-switching (2021)5.24
- Mask The Bias: Improving Domain-adaptive Generalization Of Ctc-based ASR With Internal Language Model Estimation (2023)3.58