mlsanityData to 14 Oct 2026

N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets

arXiv 2308.02092 ↗First posted 4 Aug 2023cs.CL cs.AI cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate transcription of proper names and technical terms is particularly important in speech-to-text applications for business conversations. These words, which are essential to understanding the conversation, are often rare and therefore likely to be under-represented in text and audio training data, creating a significant challenge in this domain. We present a two-step keyword boosting mechanism that successfully works on normalized unigrams and n-grams rather than just single tokens, which eliminates missing hits issues with boosting raw targets. In addition, we show how adjusting the boosting weight logic avoids over-boosting multi-token keywords. This improves our keyword recognition rate by 26% relative on our proprietary in-domain dataset and 2% on LibriSpeech. This method is particularly useful on targets that involve non-alphabetic characters or have non-standard pronunciations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 4 Aug 2023.

Builds on

13 of 18 references.

References · 13

  1. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  2. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  3. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 235
  4. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 234
  5. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  6. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
  7. 2020Contextual RNN-T For Open Domain ASRcited by 85
  8. 2019Jasper: An End-to-End Convolutional Neural Acoustic Modelcited by 76
  9. 2018A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognitioncited by 66
  10. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  11. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  12. 2014First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNscited by 28
1 more
  1. 2021Spell my name: keyword boosted speech recognitioncited by 10

Built on by

Not cited yet.