mlsanityData to 7 Oct 2026

TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree

arXiv 2508.07014 ↗First posted 9 Aug 2025eess.AS cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Recognizing specific key phrases is an essential task for contextualized Automatic Speech Recognition (ASR). However, most existing context-biasing approaches have limitations associated with the necessity of additional model training, significantly slow down the decoding process, or constrain the choice of the ASR system type. This paper proposes a universal ASR context-biasing framework that supports all major types: CTC, Transducers, and Attention Encoder-Decoder models. The framework is based on a GPU-accelerated word boosting tree, which enables it to be used in shallow fusion mode for greedy and beam search decoding without noticeable speed degradation, even with a vast number of key phrases (up to 20K items). The obtained results showed high efficiency of the proposed method, surpassing the considered open-source context-biasing approaches in accuracy and decoding speed. Our context-biasing framework is open-sourced as a part of the NeMo toolkit.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 9 Aug 2025.

Builds on

23 of 33 references.

References · 23

  1. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  2. 2015Listen, Attend and Spellcited by 542
  3. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  4. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  5. 2023End-to-End Speech Recognition: A Surveycited by 127
  6. 2023Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognitioncited by 120
  7. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  8. 2020Contextual RNN-T For Open Domain ASRcited by 85
  9. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  10. 2023SLM: Bridge the thin gap between speech and text foundation modelscited by 67
  11. 2020On the Comparison of Popular End-to-End Models for Large Scale Speech Recognitioncited by 62
  12. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 60
11 more
  1. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  2. 2023PromptASR for contextualized ASR with controllable stylecited by 18
  3. 2024Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPUcited by 12
  4. 2024Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbationcited by 11
  5. 2021Spell my name: keyword boosted speech recognitioncited by 10
  6. 2023Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithmcited by 9
  7. 2024Label-Looping: Highly Efficient Decoding for Transducerscited by 9
  8. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  9. 2024MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decodercited by 7
  10. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  11. 2025Pushing the Limits of Beam Search Decoding for Transducer-based ASR modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wildcited by 2
  2. 2025FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilitiescited by 1
  3. 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation taskcited by 0
  4. 2026TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systemscited by 0