mlsanityData to 14 Oct 2026

Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network

arXiv 2305.12493 ↗First posted 21 May 2023eess.AS cs.CL cs.SDcited by 31

Not on the map. Why?

Abstract (arXiv)

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for bias tasks. In this study, we introduce a contextual phrase prediction network for an attention-based deep bias method. This network predicts context phrases in utterances using contextual embeddings and calculates bias loss to assist in the training of the contextualized model. Our method achieved a significant word error rate (WER) reduction across various end-to-end speech recognition models. Experiments on the LibriSpeech corpus show that our proposed model obtains a 12.1% relative WER improvement over the baseline model, and the WER of the context phrases decreases relatively by 40.5%. Moreover, by applying a context phrase filtering strategy, we also effectively eliminate the WER degradation when using a larger biasing list.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 21 May 2023.

Builds on

18 of 26 references.

References · 18

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  3. 2015Listen, Attend and Spellcited by 543
  4. 2015Attention-Based Models for Speech Recognitioncited by 401
  5. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  6. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 234
  7. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  8. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
  9. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  10. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
  11. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  12. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
6 more
  1. 2018End-to-end contextual speech recognition using class language models and a token passing decodercited by 26
  2. 2020Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducercited by 22
  3. 2020CIF-based Collaborative Decoding for End-to-end Contextual Speech Recognitioncited by 21
  4. 2021Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devicescited by 19
  5. 2022Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Modelcited by 17
  6. 2023Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducercited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 13; 2026: 7.

31 papers.

Sort:

By area:

  1. 2023PromptASR for contextualized ASR with controllable stylecited by 19
  2. 2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
  3. 2024CTC-Assisted LLM-Based Contextual ASRcited by 19
  4. 2023SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Abilitycited by 18
  5. 2024Improving ASR Contextual Biasing with Guided Attentioncited by 17
  6. 2024Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Losscited by 10
  7. 2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
  8. 2026SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processingcited by 8
  9. 2025Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuningcited by 7
  10. 2023Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducercited by 6
  11. 2024Improving Domain-Specific ASR with LLM-Generated Contextual Descriptionscited by 6
  12. 2024InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictionscited by 5
19 more
  1. 2025OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabularycited by 4
  2. 2024Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrievalcited by 3
  3. 2025WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasingcited by 3
  4. 2025Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciationcited by 3
  5. 2025DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognitioncited by 2
  6. 2025Automatic Speech Recognition of African American English: Lexical and Contextual Effectscited by 2
  7. 2025Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activationcited by 1
  8. 2025CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Modelscited by 1
  9. 2025Improving Contextual ASR via Multi-grained Fusion with Large Language Modelscited by 1
  10. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  11. 2026Dolphin-CN-Dialect: Where Chinese Dialects Mattercited by 1
  12. 2026How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMscited by 1
  13. 2025Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasingcited by 0
  14. 2025Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognitioncited by 0
  15. 2025Peeking Into The Future For Contextual Biasingcited by 0
  16. 2026CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASRcited by 0
  17. 2026Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learningcited by 0
  18. 2026RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recoverycited by 0
  19. 2026BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASRcited by 0