mlsanityData to 7 Oct 2026

BERT Attends the Conversation: Improving Low-Resource Conversational ASR

arXiv 2110.02267 ↗First posted 5 Oct 2021cs.CL cs.LG eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

We propose new, data-efficient training tasks for BERT models that improve performance of automatic speech recognition (ASR) systems on conversational speech. We include past conversational context and fine-tune BERT on transcript disambiguation without external data to rescore ASR candidates. Our results show word error rate recoveries up to 37.2%. We test our methods in low-resource data domains, both in language (Norwegian), tone (spontaneous, conversational), and topics (parliament proceedings and customer service phone calls). These techniques are applicable to any ASR system and do not require any additional data, provided a pre-trained BERT model. We also show how the performance of our context-augmented rescoring methods strongly depends on the degree of spontaneity and nature of the conversation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

17 of 37 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  6. 2018Deep contextualized word representationscited by 2,285
  7. 2015Listen, Attend and Spellcited by 542
  8. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  9. 2015Attention-Based Models for Speech Recognitioncited by 400
  10. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  11. 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
  12. 2020Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trendscited by 28
5 more
  1. 2018Dialog-context aware end-to-end speech recognitioncited by 27
  2. 2021Innovative Bert-based Reranking Language Models for Speech Recognitioncited by 23
  3. 2019Cross-Attention End-to-End ASR for Two-Party Conversationscited by 14
  4. 2019An Empirical Study of Efficient ASR Rescoring with Transformerscited by 11
  5. 2021ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modelingcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2022The Norwegian Parliamentary Speech Corpuscited by 7
  2. 2023Boosting Norwegian Automatic Speech Recognitioncited by 2
  3. 2024Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learningcited by 2
  4. 2025Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASRcited by 0