mlsanityData to 14 Oct 2026

Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation

arXiv 2309.07369 ↗First posted 14 Sep 2023eess.AS cs.CL cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text adaptation. In particular, effective, quick and inexpensive adaptation with text input has become a primary concern for deploying AED systems in the industry. To address this issue, we propose a novel model, the hybrid attention-based encoder-decoder (HAED) speech recognition model that preserves the modularity of conventional hybrid automatic speech recognition systems. Our HAED model separates the acoustic and language models, allowing for the use of conventional text-based language model adaptation techniques. We demonstrate that the proposed HAED model yields 23% relative Word Error Rate (WER) improvements when out-of-domain text data is used for language model adaptation, with only a minor degradation in WER on a general test set compared with the conventional AED model.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 14 Sep 2023.

Builds on

24 of 34 references.

References · 24

  1. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 257
  2. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  3. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  4. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 150
  5. 2020Hybrid Autoregressive Transducer (hat)cited by 108
  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. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
  9. 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
  10. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  11. 2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
  12. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 32
12 more
  1. 2021Librispeech Transducer Model with Internal Language Model Prior Correctioncited by 26
  2. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
  3. 2021On Addressing Practical Challenges for RNN-Transducercited by 19
  4. 2022Modular Hybrid Autoregressive Transducercited by 17
  5. 2022Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition modelscited by 11
  6. 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
  7. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  8. 2023Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmaxcited by 8
  9. 2022LongFNT: Long-form Speech Recognition with Factorized Neural Transducercited by 6
  10. 2022Residual Language Model for End-to-end Speech Recognitioncited by 5
  11. 2023Decoupled Structure for Improved Adaptability of End-to-End Modelscited by 3
  12. 2023External Language Model Integration for Factorized Neural Transducerscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformerscited by 0