# Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning

arXiv: https://arxiv.org/abs/2408.06043 · HTML: https://mlsanity.com/paper/2408.06043/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 12 Aug 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Towards end-to-end spoken language understanding](https://mlsanity.com/paper/1802.08395/) (2018)
- [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://mlsanity.com/paper/2107.05782/) (2021)
- [ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet](https://mlsanity.com/paper/2111.14706/) (2021)
- ["How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations](https://mlsanity.com/paper/2109.13489/) (2021)
- [Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding](https://mlsanity.com/paper/1912.07240/) (2019)
- [Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding](https://mlsanity.com/paper/1909.10861/) (2019)
- [Retrieval Augmented End-to-End Spoken Dialog Models](https://mlsanity.com/paper/2402.01828/) (2024)
- [Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors](https://mlsanity.com/paper/2006.05635/) (2020)
- [SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives](https://mlsanity.com/paper/2305.13192/) (2023)
- [Adapting Long Context NLM for ASR Rescoring in Conversational Agents](https://mlsanity.com/paper/2104.11070/) (2021)
- [TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations](https://mlsanity.com/paper/2112.12441/) (2021)
- [Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation](https://mlsanity.com/paper/2309.08876/) (2023)
- [ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2305.14838/) (2023)
- [Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding](https://mlsanity.com/paper/2306.07944/) (2023)
- [Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering](https://mlsanity.com/paper/2305.16335/) (2023)
- [BERT Attends the Conversation: Improving Low-Resource Conversational ASR](https://mlsanity.com/paper/2110.02267/) (2021)

## Built on by (most cited first, 2 of 2)

- [Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR](https://mlsanity.com/paper/2603.26246/) (2026)
- [From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs](https://mlsanity.com/paper/2603.24034/) (2026)

## Abstract (arXiv)

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and agent interactions for transcribing subsequent utterances has been proposed. This method incorporates the transcription of the user's speech and the agent's response as model input, using the accumulated context generated by each turn. However, this context is susceptible to ASR errors because it is generated by the ASR model in an auto-regressive fashion. Such noisy context can further degrade the benefits of context input, resulting in suboptimal ASR performance. In this paper, we introduce Context Noise Representation Learning (CNRL) to enhance robustness against noisy context, ultimately improving dialogue speech recognition accuracy. To maximize the advantage of context awareness, our approach includes decoder pre-training using text-based dialogue data and noise representation learning for a context encoder. Based on the evaluation of speech dialogues, our method shows superior results compared to baselines. Furthermore, the strength of our approach is highlighted in noisy environments where user speech is barely audible due to real-world noise, relying on contextual information to transcribe the input accurately.