DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
Not on the map. Why?
Abstract (arXiv)
Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method improves CB accuracy but with slow inference speed. While dynamic vocabulary can be applied to non-autoregressive (NAR) models, such as connectionist temporal classification (CTC), the conditional independence assumption fails to capture dependencies between static and dynamic tokens. This paper proposes DYNAC (Dynamic Vocabulary-based NAR Contextualization), a self-conditioned CTC method that integrates dynamic vocabulary into intermediate layers. Conditioning the encoder on dynamic vocabulary, DYNAC effectively captures dependencies between static and dynamic tokens while reducing the real-time factor (RTF). Experimental results show that DYNAC reduces RTF by 81% with a 0.1-point degradation in word error rate on the LibriSpeech 960 test-clean set.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 31 May 2025.
Builds on
33 of 41 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
- 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
- 2015Listen, Attend and Spellcited by 543
- 2015Attention-Based Models for Speech Recognitioncited by 401
- 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
- 2018Deep context: end-to-end contextual speech recognitioncited by 137
- 2023End-to-End Speech Recognition: A Surveycited by 129
- 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
- 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 96
21 more
- 2020Contextual RNN-T For Open Domain ASRcited by 85
- 2020Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predictcited by 76
- 2024OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformercited by 74
- 2020Imputer: Sequence Modelling via Imputation and Dynamic Programmingcited by 66
- 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
- 2020Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignmentcited by 37
- 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 37
- 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
- 2021Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognitioncited by 30
- 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 28
- 2019Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networkscited by 24
- 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
- 2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 14
- 2023Phoneme-aware Encoding for Prefix-tree-based Contextual ASRcited by 13
- 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 10
- 2023Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentationcited by 9
- 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
- 2023Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducercited by 6
- 2023Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimationcited by 5
- 2024InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictionscited by 5
- 2024Joint Beam Search Integrating CTC, Attention, and Transducer Decoderscited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.