mlsanityData to 7 Oct 2026

Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition

arXiv 2110.02220 ↗First posted 5 Oct 2021eess.AS cs.AI cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result. However, the traditional re-scoring approaches based on an external language model is prone to diverge during the personalized training. In this work, we introduce a model-based end-to-end contextual adaptation approach that is decoder-agnostic and amenable to on-device personalization. Our on-device simulation experiments demonstrate that the proposed approach outperforms the traditional re-scoring technique by 12% relative WER and 15.7% entity mention specific F1-score in a continues personalization scenario.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

22 of 28 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  9. 2015Listen, Attend and Spellcited by 542
  10. 2017Meta Networkscited by 268
  11. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  12. 2020Contextual RNN-T For Open Domain ASRcited by 85
10 more
  1. 2020Cascaded encoders for unifying streaming and non-streaming ASRcited by 51
  2. 2020Learning Associative Inference Using Fast Weight Memorycited by 51
  3. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  4. 2021Approximating How Single Head Attention Learnscited by 38
  5. 2018Toward domain-invariant speech recognition via large scale trainingcited by 35
  6. 2018Contextual Speech Recognition with Difficult Negative Training Examplescited by 28
  7. 2016Personalized Speech recognition on mobile devicescited by 23
  8. 2019Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Inductioncited by 15
  9. 2016Neural Semantic Encoderscited by 14
  10. 2020Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modellingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 7; 2025: 3; 2026: 2.

25 papers.

Sort:

By area:

  1. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  2. 2024Improving ASR Contextual Biasing with Guided Attentioncited by 17
  3. 2023Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuningcited by 13
  4. 2023CB-Conformer: Contextual biasing Conformer for biased word recognitioncited by 11
  5. 2023Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithmcited by 9
  6. 2023Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognitioncited by 8
  7. 2023Retrieve and Copy: Scaling ASR Personalization to Large Catalogscited by 7
  8. 2022CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signalscited by 5
  9. 2023Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognitioncited by 5
  10. 2023A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spottingcited by 5
  11. 2024Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASRcited by 5
  12. 2022Continual Learning for On-Device Speech Recognition using Disentangled Conformerscited by 4
13 more
  1. 2024Locality enhanced dynamic biasing and sampling strategies for contextual ASRcited by 3
  2. 2024Text Injection for Neural Contextual Biasingcited by 3
  3. 2024Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrievalcited by 3
  4. 2023Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentationcited by 2
  5. 2023Adaptive Endpointing with Deep Contextual Multi-armed Banditscited by 1
  6. 2025Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modelingcited by 1
  7. 2025A Neural Model for Contextual Biasing Score Learning and Filteringcited by 1
  8. 2023Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducercited by 0
  9. 2024High-precision Voice Search Query Correction via Retrievable Speech-text Embedingscited by 0
  10. 2024An Efficient Self-Learning Framework For Interactive Spoken Dialog Systemscited by 0
  11. 2025H-PRM: A Pluggable Hotword Pre-Retrieval Module for Various Speech Recognition Systemscited by 0
  12. 2026RASST: Retrieval-Augmented Simultaneous Speech Translationcited by 0
  13. 2026BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASRcited by 0