Challenge: Recent work has shown poor performance with non-Indo-European languages . previous work primarily utilizes video information to build VSR models .
Approach: They propose a generative model for data inflation that integrates synthetic data with authentic visual data to enhance the VSR model.
Outcome: The proposed model improves on the audio-visual alignment problem in audio-video tasks.

Similar Papers

XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception (2024.acl-long)

Copied to clipboard

Challenge: Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments.
Approach: They propose a cross-lingual audio-visual speech representation model for noise-robust speech recognition and translation in over 100 languages.
Outcome: The proposed model outperforms the previous state-of-the-art by 18.5% WER and 4.7 BLEU on downstream audio-visual speech recognition and translation tasks.
AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: Existing models for speech-to-speech translation suffer from distinct degradation in noisy environments and fail to translate visual speech.
Approach: They propose a text-based audio-visual speech-to-speech translation model that integrates visual information with audio-only data to improve system robustness.
Outcome: The proposed model outperforms models trained on audio-only corpus in two languages . it also improves with low-resource audio-visual data, compared with baselines .
Multimodal and Multiresolution Speech Recognition with Transformers (2020.acl-main)

Copied to clipboard

Challenge: Existing audio visual automatic speech recognition systems rely on audio input to produce transcriptions.
Approach: They propose an audio visual automatic speech recognition system using a transformer-based architecture and incorporate a multitask training criterion for multiresolution ASR.
Outcome: The proposed system can generate character and subword transcriptions with visual information.
On Generative Spoken Language Modeling from Raw Audio (2021.tacl-1)

Copied to clipboard

Challenge: Using a set of metrics to evaluate the learned representations, we aim to create a system that learns from natural interactions as infants learn their first language.
Approach: They propose a task of learning acoustic and linguistic characteristics from raw audio and a set of metrics to evaluate the learned representations at acustic, linguistic and encoding levels.
Outcome: The proposed models evaluate the learned representations at acoustic and linguistic levels for both encoding and generation.
A Survey of Multilingual Models for Automatic Speech Recognition (2022.lrec-1)

Copied to clipboard

Challenge: Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, but the majority of the world’s languages do not have usable systems due to the lack of large speech datasets to train these models.
Approach: They propose to use unlabeled speech data to build multilingual ASR models that can be used for improved performance on low-resource languages.
Outcome: The proposed models can be used to improve performance on low-resource languages by using unlabeled speech data.
Intuitive Multilingual Audio-Visual Speech Recognition with a Single-Trained Model (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that multilingual models outperform monolingual ones.
Approach: They propose a single model that can capture which language is given as input speech . they use a pre-trained model to fine-tune the model so it can recognize the language class as well as the speech with the corresponding language.
Outcome: The proposed model can recognize which language is given as input speech . it can accurately recognize speech in noisy environments, such as crowded restaurants .
Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition (2023.acl-long)

Copied to clipboard

Challenge: Existing efforts to improve robustness of audio-visual speech recognition with visual information focus on audio modality . current approaches introduce noise adaptation techniques to improve reliability of AVSR task .
Approach: They propose a visual-invariant modality to strengthen robustness of audio-visual speech recognition (AVSR) it can adapt to any testing noises without dependence on noisy training data, a.k.a., unsupervised noise adaptation.
Outcome: The proposed method outperforms existing state-of-the-arts on visual speech recognition task under various noisy and clean conditions.
Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: AVLM integrates full-face visual cues into a pre-trained expressive speech model.
Approach: They propose an Audio-Visual Language Model (AVLM) for expressive speech generation by integrating full-face visual cues into a pre-trained expressive speech model.
Outcome: The proposed model incorporates full-face visual cues into a pre-trained expressive speech model.
The Effects of Pretraining in Video-Guided Machine Translation (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to improve VMT models integrate text and video modalities.
Approach: They propose an approach that improves the performance of VMT models by using a new dataset which contains transcribed audio descriptions of movies.
Outcome: The proposed model improves on the MAD (Movie Audio Descriptions) dataset.
Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding (2023.emnlp-demo)

Copied to clipboard

Challenge: Large Language Models (LLMs) are capable of understanding multi-modal content, but textonly human-computer interaction is not sufficient for many application scenarios.
Approach: They propose a video-to-text generation task and a multi-modal framework that bootstraps cross-modal training from frozen pre-trained visual & audio encoders and frozen LLMs.
Outcome: The proposed framework can understand both visual and auditory content in video and generate meaningful responses grounded in the visual and audio information presented in the videos.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations