# MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition

arXiv: https://arxiv.org/abs/2303.05309 · HTML: https://mlsanity.com/paper/2303.05309/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 72 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](https://mlsanity.com/paper/2204.09934/) (2022)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [ASR is all you need: cross-modal distillation for lip reading](https://mlsanity.com/paper/1911.12747/) (2019)
- [LipNet: End-to-End Sentence-level Lipreading](https://mlsanity.com/paper/1611.01599/) (2016)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization](https://mlsanity.com/paper/2106.04185/) (2021)
- [Sub-word Level Lip Reading With Visual Attention](https://mlsanity.com/paper/2110.07603/) (2021)
- [End-to-End Speech Translation with Knowledge Distillation](https://mlsanity.com/paper/1904.08075/) (2019)
- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild](https://mlsanity.com/paper/1810.06990/) (2018)

## Built on by (most cited first, 14 of 14)

- [Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing](https://mlsanity.com/paper/2402.15151/) (2024)
- [MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens](https://mlsanity.com/paper/2503.11315/) (2025)
- [AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation](https://mlsanity.com/paper/2312.02512/) (2023)
- [XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception](https://mlsanity.com/paper/2403.14402/) (2024)
- [OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment](https://mlsanity.com/paper/2306.06410/) (2023)
- [SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing](https://mlsanity.com/paper/2409.03605/) (2024)
- [Wav2SQL: Direct Generalizable Speech-To-SQL Parsing](https://mlsanity.com/paper/2305.12552/) (2023)
- [TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation](https://mlsanity.com/paper/2312.15197/) (2023)
- [Language Model is a Branch Predictor for Simultaneous Machine Translation](https://mlsanity.com/paper/2312.14488/) (2023)
- [Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation](https://mlsanity.com/paper/2408.01732/) (2024)
- [Gesture-Aware Zero-Shot Speech Recognition for Patients with Language Disorders](https://mlsanity.com/paper/2502.13983/) (2025)
- [TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal](https://mlsanity.com/paper/2508.07878/) (2025)
- [Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation](https://mlsanity.com/paper/2412.16530/) (2024)
- [DoubleHelix: Structured Cross-Modal Fusion for Audio-Visual Speech Recognition with LLMs](https://mlsanity.com/paper/2607.29112/) (2026)

## Abstract (arXiv)

Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present AVMuST-TED, the first dataset for Audio-Visual Multilingual Speech Translation, derived from TED talks. Nonetheless, visual speech is not as distinguishable as audio speech, making it difficult to develop a mapping from source speech phonemes to the target language text. To address this issue, we propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. To further minimize the cross-modality gap and its impact on knowledge transfer, we suggest adopting mixed speech, which is created by interpolating audio and visual streams, along with a curriculum learning strategy to adjust the mixing ratio as needed. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2. Moreover, it achieves state-of-the-art performance in lip reading on CMLR (11.1%), LRS2 (25.5%), and LRS3 (28.0%).