mlsanityData to 14 Oct 2026

External Language Model Integration for Factorized Neural Transducers

arXiv 2305.17304 ↗First posted 26 May 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly more value when linearly interpolated with predictor output compared to shallow fusion, thus confirming that FNT forces the predictor to act like regular language models. Further, we propose a method to integrate class-based n-gram language models into FNT framework resulting in accuracy gains similar to a hybrid setup. We show average gains of 18% WERR with lexical adaptation across various scenarios and additive gains of up to 60% WERR in one entity-rich scenario through a combination of class-based n-gram and neural LMs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

25 of 33 references.

References · 25

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  3. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 150
  4. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  5. 2020Hybrid Autoregressive Transducer (hat)cited by 108
  6. 2016Towards better decoding and language model integration in sequence to sequence modelscited by 100
  7. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 100
  8. 2017Cold Fusion: Training Seq2Seq Models Together with Language Modelscited by 88
  9. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  10. 2020A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognitioncited by 73
  11. 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
  12. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
13 more
  1. 2020Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capabilitycited by 63
  2. 2021SynthASR: Unlocking Synthetic Data for Speech Recognitioncited by 34
  3. 2022RescoreBERT: Discriminative Speech Recognition Rescoring with BERTcited by 34
  4. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 32
  5. 2021Innovative Bert-based Reranking Language Models for Speech Recognitioncited by 23
  6. 2021On Addressing Practical Challenges for RNN-Transducercited by 19
  7. 2021On Language Model Integration for RNN Transducer based Speech Recognitioncited by 17
  8. 2022Modular Hybrid Autoregressive Transducercited by 17
  9. 2020Accelerating RNN Transducer Inference via One-Step Constrained Beam Searchcited by 13
  10. 2022Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition modelscited by 11
  11. 2020High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Modelcited by 8
  12. 2021Language model fusion for streaming end to end speech recognitioncited by 8
  13. 2022Neural-FST Class Language Model for End-to-End Speech Recognitioncited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Improved Factorized Neural Transducer Model For text-only Domain Adaptationcited by 2
  2. 2023Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptationcited by 1