mlsanityData to 14 Oct 2026

Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition

arXiv 2207.04176 ↗First posted 9 Jul 2022eess.AS cs.CL cs.SDcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 9 Jul 2022.

Builds on

26 of 39 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  4. 2020Hybrid Autoregressive Transducer (hat)cited by 108
  5. 2017Cold Fusion: Training Seq2Seq Models Together with Language Modelscited by 88
  6. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  7. 2020A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognitioncited by 73
  8. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  9. 2020The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Resultscited by 44
  10. 2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
  11. 2018On the End-to-End Solution to Mandarin-English Code-switching Speech Recognitioncited by 30
  12. 2020Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognitioncited by 28
14 more
  1. 2018Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentationcited by 26
  2. 2021Librispeech Transducer Model with Internal Language Model Prior Correctioncited by 26
  3. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
  4. 2020Data Augmentation for End-to-end Code-switching Speech Recognitioncited by 20
  5. 2021Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorizationcited by 18
  6. 2018Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speechcited by 12
  7. 2021Minimum word error training for non-autoregressive Transformer-based code-switching ASRcited by 9
  8. 2021Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networkscited by 9
  9. 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
  10. 2018Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognitioncited by 7
  11. 2019Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Datacited by 7
  12. 2019Training a code-switching language model with monolingual datacited by 6
  13. 2020Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognitioncited by 5
  14. 2020End-to-End Code Switching Language Models for Automatic Speech Recognitioncited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 2.

5 papers.

  1. 2023BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognitioncited by 9
  2. 2023Generative error correction for code-switching speech recognition using large language modelscited by 7
  3. 2024Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decodingcited by 7
  4. 2025Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuningcited by 5
  5. 2025Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Reviewcited by 4