mlsanityData to 7 Oct 2026

Librispeech Transducer Model with Internal Language Model Prior Correction

arXiv 2104.03006 ↗First posted 7 Apr 2021cs.CL cs.AI stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where the transducer model prior is given by the estimated internal LM. The subtraction of the internal LM gives us over 14% relative improvement over normal shallow fusion. Our transducer has a separate probability distribution for the non-blank labels which allows for easier combination with the external LM, and easier estimation of the internal LM. We additionally take care of including the end-of-sentence (EOS) probability of the external LM in the last blank probability which further improves the performance. All our code and setups are published.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 17 of its 28 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

17 of 28 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  5. 2018Horovod: fast and easy distributed deep learning in TensorFlowcited by 275
  6. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 232
  7. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  8. 2020Hybrid Autoregressive Transducer (hat)cited by 106
  9. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 96
  10. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  11. 2020A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognitioncited by 73
  12. 2019RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentationcited by 63
5 more
  1. 2016Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activationscited by 54
  2. 2018Improved training of end-to-end attention models for speech recognitioncited by 35
  3. 2020A New Training Pipeline for an Improved Neural Transducercited by 34
  4. 2018RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognitioncited by 30
  5. 2020Phoneme Based Neural Transducer for Large Vocabulary Speech Recognitioncited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 5; 2024: 2; 2025: 6; 2026: 2.

26 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2023End-to-End Speech Recognition: A Surveycited by 127
  3. 2025Ming-Omni: A Unified Multimodal Model for Perception and Generationcited by 62
  4. 2025Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generationcited by 21
  5. 2025M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performancecited by 19
  6. 2021Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognitioncited by 17
  7. 2021On Language Model Integration for RNN Transducer based Speech Recognitioncited by 17
  8. 2022Modular Hybrid Autoregressive Transducercited by 17
  9. 2025Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representationcited by 15
  10. 2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
  11. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  12. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
14 more
  1. 2023Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognitioncited by 7
  2. 2022Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognitioncited by 5
  3. 2021PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognitioncited by 3
  4. 2024Effective internal language model training and fusion for factorized transducer modelcited by 3
  5. 2024Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognitioncited by 3
  6. 2021Back from the future: bidirectional CTC decoding using future information in speech recognitioncited by 2
  7. 2022Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptationcited by 2
  8. 2023Improving Language Model Integration for Neural Machine Translationcited by 2
  9. 2025Label-Context-Dependent Internal Language Model Estimation for CTCcited by 2
  10. 2022AutoLV: Automatic Lecture Video Generatorcited by 1
  11. 2023Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptationcited by 1
  12. 2025OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMscited by 0
  13. 2026Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancementcited by 0
  14. 2026Diffusion Language Models for Speech Recognitioncited by 0