mlsanityData to 7 Oct 2026

Conversational Speech Recognition By Learning Conversation-level Characteristics

arXiv 2202.07855 ↗First posted 16 Feb 2022cs.SD cs.CL eess.AScited by 8

Not on the map. Why?

Abstract (arXiv)

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of conversation, such as role preference and topical coherence. This paper proposes a conversational ASR model which explicitly learns conversation-level characteristics under the prevalent end-to-end neural framework. The highlights of the proposed model are twofold. First, a latent variational module (LVM) is attached to a conformer-based encoder-decoder ASR backbone to learn role preference and topical coherence. Second, a topic model is specifically adopted to bias the outputs of the decoder to words in the predicted topics. Experiments on two Mandarin conversational ASR tasks show that the proposed model achieves a maximum 12% relative character error rate (CER) reduction.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

21 of 30 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Longformer: The Long-Document Transformercited by 3,362
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  7. 2015Listen, Attend and Spellcited by 542
  8. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  9. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 210
  10. 2017State-of-the-art Speech Recognition With Sequence-to-Sequence Modelscited by 196
  11. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  12. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
9 more
  1. 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
  2. 2017Exploiting Cross-Sentence Context for Neural Machine Translationcited by 48
  3. 2018Dialog-context aware end-to-end speech recognitioncited by 27
  4. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  5. 2020Simplified Self-Attention for Transformer-based End-to-End Speech Recognitioncited by 20
  6. 2021Modeling Bilingual Conversational Characteristics for Neural Chat Translationcited by 18
  7. 2019Cross-Attention End-to-End ASR for Two-Party Conversationscited by 14
  8. 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillationcited by 12
  9. 2021Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognitioncited by 9

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 2.

8 papers.

  1. 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASRcited by 7
  2. 2022Context-aware Fine-tuning of Self-supervised Speech Modelscited by 7
  3. 2022LongFNT: Long-form Speech Recognition with Factorized Neural Transducercited by 6
  4. 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representationcited by 4
  5. 2024Target conversation extraction: Source separation using turn-taking dynamicscited by 4
  6. 2023Generative Context-aware Fine-tuning of Self-supervised Speech Modelscited by 3
  7. 2025Proactive Hearing Assistants that Isolate Egocentric Conversationscited by 1
  8. 2025Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASRcited by 0