mlsanityData to 7 Oct 2026

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter

arXiv 2406.07096 ↗First posted 11 Jun 2024eess.AS cs.AI cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modification of the ASR model or the beam-search decoding algorithm, complicating model reuse and slowing down inference. This work presents a new approach to fast context-biasing with CTC-based Word Spotter (CTC-WS) for CTC and Transducer (RNN-T) ASR models. The proposed method matches CTC log-probabilities against a compact context graph to detect potential context-biasing candidates. The valid candidates then replace their greedy recognition counterparts in corresponding frame intervals. A Hybrid Transducer-CTC model enables the CTC-WS application for the Transducer model. The results demonstrate a significant acceleration of the context-biasing recognition with a simultaneous improvement in F-score and WER compared to baseline methods. The proposed method is publicly available in the NVIDIA NeMo toolkit.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

18 of 27 references.

References · 18

  1. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  2. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 189
  3. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  4. 2023Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognitioncited by 120
  5. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  6. 2020Contextual RNN-T For Open Domain ASRcited by 85
  7. 2020CTC-Segmentation of Large Corpora for German End-to-end Speech Recognitioncited by 75
  8. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  9. 2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
  10. 2021NeMo Inverse Text Normalization: From Development To Productioncited by 28
  11. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  12. 2021Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devicescited by 18
6 more
  1. 2023PromptASR for contextualized ASR with controllable stylecited by 18
  2. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  3. 2020Accelerating RNN Transducer Inference via One-Step Constrained Beam Searchcited by 13
  4. 2021Spell my name: keyword boosted speech recognitioncited by 10
  5. 2023GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognitioncited by 4
  6. 2021Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognitioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  2. 2025Pushing the Limits of Beam Search Decoding for Transducer-based ASR modelscited by 4
  3. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4
  4. 2026Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wildcited by 2
  5. 2026TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systemscited by 0
  6. 2026PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMscited by 0
  7. 2026BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASRcited by 0