Cross-Attention End-to-End ASR for Two-Party Conversations
Not on the map. Why?
Abstract (arXiv)
We present an end-to-end speech recognition model that learns interaction between two speakers based on the turn-changing information. Unlike conventional speech recognition models, our model exploits two speakers' history of conversational-context information that spans across multiple turns within an end-to-end framework. Specifically, we propose a speaker-specific cross-attention mechanism that can look at the output of the other speaker side as well as the one of the current speaker for better at recognizing long conversations. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 4; 2023: 4; 2024: 0; 2025: 1.
14 papers.
Sort:
- 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnetcited by 53
- 2022Conversational Speech Recognition By Learning Conversation-level Characteristicscited by 8
- 2021Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognitioncited by 7
- 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASRcited by 7
- 2022Context-aware Fine-tuning of Self-supervised Speech Modelscited by 7
- 2021Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understandingcited by 5
- 2021BERT Attends the Conversation: Improving Low-Resource Conversational ASRcited by 4
- 2022Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanismcited by 4
- 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representationcited by 4
- 2023Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog Historycited by 3
- 2023Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilizationcited by 3
- 2023Generative Context-aware Fine-tuning of Self-supervised Speech Modelscited by 3
- 2025Cross-Attention is Half Explanation in Speech-to-Text Models22 Sep 2025
- 2023Generative Context-aware Fine-tuning of Self-supervised Speech Models15 Dec 2023
- 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation22 Oct 2023
- 2023Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization27 Sep 2023
- 2023Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History1 May 2023
- 2022Context-aware Fine-tuning of Self-supervised Speech Models16 Dec 2022
- 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR3 Jul 2022
- 2022Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism2 Jul 2022
- 2022Conversational Speech Recognition By Learning Conversation-level Characteristics16 Feb 2022
- 2021Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding13 Dec 2021
- 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet29 Nov 2021
- 2021BERT Attends the Conversation: Improving Low-Resource Conversational ASR5 Oct 2021
- 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnetcited by 53
- 2022Conversational Speech Recognition By Learning Conversation-level Characteristicscited by 8
- 2021Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognitioncited by 7
- 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASRcited by 7
- 2022Context-aware Fine-tuning of Self-supervised Speech Modelscited by 7
- 2021Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understandingcited by 5
- 2021BERT Attends the Conversation: Improving Low-Resource Conversational ASRcited by 4
- 2022Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanismcited by 4
- 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representationcited by 4
- 2023Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog Historycited by 3
- 2023Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilizationcited by 3
- 2023Generative Context-aware Fine-tuning of Self-supervised Speech Modelscited by 3
12 most cited of 14 All 14 (JSON)
- 2025Cross-Attention is Half Explanation in Speech-to-Text Models22 Sep 2025
- 2023Generative Context-aware Fine-tuning of Self-supervised Speech Models15 Dec 2023
- 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation22 Oct 2023
- 2023Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization27 Sep 2023
- 2023Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History1 May 2023
- 2022Context-aware Fine-tuning of Self-supervised Speech Models16 Dec 2022
- 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR3 Jul 2022
- 2022Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism2 Jul 2022
- 2022Conversational Speech Recognition By Learning Conversation-level Characteristics16 Feb 2022
- 2021Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding13 Dec 2021
- 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet29 Nov 2021
- 2021BERT Attends the Conversation: Improving Low-Resource Conversational ASR5 Oct 2021
12 newest of 14 All 14 (JSON)