mlsanityData to 7 Oct 2026

Neural-FST Class Language Model for End-to-End Speech Recognition

arXiv 2201.11867 ↗First posted 28 Jan 2022cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic background text together with a collection of domain-specific entities modeled as individual FSTs. Each output token is generated by a mixture of these components; the mixture weights are estimated with a separately trained neural decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative in terms of Word Error Rate. NFCLM achieves similar performance as traditional NNLM and FST shallow fusion while being less prone to overbiasing and 12 times more compact, making it more suitable for on-device usage.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

16 of 33 references.

References · 16

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  3. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
  4. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  5. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  6. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 111
  7. 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 109
  8. 2020Hybrid Autoregressive Transducer (hat)cited by 106
  9. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  10. 2017Cold Fusion: Training Seq2Seq Models Together with Language Modelscited by 87
  11. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  12. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
4 more
  1. 2019Speech Recognition with Augmented Synthesized Speechcited by 60
  2. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  3. 2020Alignment Restricted Streaming Recurrent Neural Network Transducercited by 42
  4. 2020Attention based on-device streaming speech recognition with large speech corpuscited by 17

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4.

6 papers.

  1. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  2. 2023Contextual Biasing of Named-Entities with Large Language Modelscited by 7
  3. 2022End-to-end Spoken Language Understanding with Tree-constrained Pointer Generatorcited by 6
  4. 2023Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Datacited by 3
  5. 2023External Language Model Integration for Factorized Neural Transducerscited by 2
  6. 2023Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducercited by 0