mlsanityData to 14 Oct 2026

Implementing contextual biasing in GPU decoder for online ASR

arXiv 2306.15685 ↗First posted 23 Jun 2023eess.AS cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

GPU decoding significantly accelerates the output of ASR predictions. While GPUs are already being used for online ASR decoding, post-processing and rescoring on GPUs have not been properly investigated yet. Rescoring with available contextual information can considerably improve ASR predictions. Previous studies have proven the viability of lattice rescoring in decoding and biasing language model (LM) weights in offline and online CPU scenarios. In real-time GPU decoding, partial recognition hypotheses are produced without lattice generation, which makes the implementation of biasing more complex. The paper proposes and describes an approach to integrate contextual biasing in real-time GPU decoding while exploiting the standard Kaldi GPU decoder. Besides the biasing of partial ASR predictions, our approach also permits dynamic context switching allowing a flexible rescoring per each speech segment directly on GPU. The code is publicly released and tested with open-sourced test sets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

14 of 31 references.

References · 14

  1. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  2. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 62
  3. 2022How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communicationscited by 30
  4. 2018End-to-end contextual speech recognition using class language models and a token passing decodercited by 26
  5. 2022ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communicationscited by 19
  6. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  7. 2021Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systemscited by 12
  8. 2021Improving callsign recognition with air-surveillance data in air-traffic communicationcited by 11
  9. 2021A Parallelizable Lattice Rescoring Strategy with Neural Language Modelscited by 10
  10. 2022A two-step approach to leverage contextual data: speech recognition in air-traffic communicationscited by 8
  11. 2018Composing Finite State Transducers on GPUscited by 4
  12. 2019GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech Recognitioncited by 4
2 more
  1. 2018A GPU-based WFST Decoder with Exact Lattice Generationcited by 3
  2. 2023Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understandingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024Unifying Global and Near-Context Biasing in a Single Trie Passcited by 1
  2. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  3. 2025Efficient Trie-based Biasing using K-step Prediction for Rare Word Recognitioncited by 0
  4. 2026Massive Open-Vocabulary Keyword Spottingcited by 0