# Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR

arXiv: https://arxiv.org/abs/2207.01039 · HTML: https://mlsanity.com/paper/2207.01039/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 3 Jul 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence](https://mlsanity.com/paper/2004.03974/) (2020)
- [Dialog-context aware end-to-end speech recognition](https://mlsanity.com/paper/1808.02171/) (2018)
- [Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers](https://mlsanity.com/paper/2104.09426/) (2021)
- [OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation](https://mlsanity.com/paper/2107.00249/) (2021)
- [Cross-Attention End-to-End ASR for Two-Party Conversations](https://mlsanity.com/paper/1907.10726/) (2019)
- [Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillation](https://mlsanity.com/paper/2102.07935/) (2021)
- [Conversational Speech Recognition By Learning Conversation-level Characteristics](https://mlsanity.com/paper/2202.07855/) (2022)
- [Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognition](https://mlsanity.com/paper/2106.06922/) (2021)

## Built on by (most cited first, 7 of 7)

- [Updated Corpora and Benchmarks for Long-Form Speech Recognition](https://mlsanity.com/paper/2309.15013/) (2023)
- [Context-aware Fine-tuning of Self-supervised Speech Models](https://mlsanity.com/paper/2212.08542/) (2022)
- [LongFNT: Long-form Speech Recognition with Factorized Neural Transducer](https://mlsanity.com/paper/2211.09412/) (2022)
- [Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems](https://mlsanity.com/paper/2306.13307/) (2023)
- [Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation](https://mlsanity.com/paper/2310.14278/) (2023)
- [Generative Context-aware Fine-tuning of Self-supervised Speech Models](https://mlsanity.com/paper/2312.09895/) (2023)
- [Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR](https://mlsanity.com/paper/2409.08797/) (2024)

## Abstract (arXiv)

Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias the current recognized hypothesis due to the inevitable historicalrecognition errors. To avoid this problem, we propose an audio-textual cross-modal representation extractor to learn contextual representations directly from preceding speech. Specifically, it consists of two modal-related encoders, extracting high-level latent features from speech and the corresponding text, and a cross-modal encoder, which aims to learn the correlation between speech and text. We randomly mask some input tokens and input sequences of each modality. Then a token-missing or modal-missing prediction with a modal-level CTC loss on the cross-modal encoder is performed. Thus, the model captures not only the bi-directional context dependencies in a specific modality but also relationships between different modalities. Then, during the training of the conversational ASR system, the extractor will be frozen to extract the textual representation of preceding speech, while such representation is used as context fed to the ASR decoder through attention mechanism. The effectiveness of the proposed approach is validated on several Mandarin conversation corpora and the highest character error rate (CER) reduction up to 16% is achieved on the MagicData dataset.