Visual Speech Recognition (lip-reading) has witnessed tremendous improvements, reaching word error rates as low as 12.8 WER in English. However, the performance in other languages is lagging far behind, due to the lack of labeled multilingual video data. In this work, we reduce the performance gap with the help of three key advances: (i) introducing the largest multilingual lip-reading dataset to date, (ii) proposing a single multi-task architecture that can perform two tasks simultaneously: identify the language and transcribe the utterance, and (iii) jointly training this architecture on all the languages together, resulting in large WER improvements as opposed to training monolingual models separately. We achieve state-of-the-art performance in both visual language identification and multilingual lip-reading tasks. Moreover, our pipeline uses zero manual annotations, as all the training transcriptions are obtained using a pre-trained ASR model. We also show that our multilingual model can be readily fine-tuned for new low-resource languages on which models trained from scratch do not converge. Our data, code, and models are available at: www.robots.ox.ac.uk/∼vgg/research/multivsr.

Co-speech gestures play a vital role in non-verbal communication. In this paper, we introduce a new framework for co-speech gesture understanding in the wild. Specifically, we propose three new tasks and benchmarks to evaluate a model's capability to comprehend gesture-speech-text associations: (i) gesture based retrieval, (ii) gesture word spotting, and (iii) active speaker detection using gestures. We present a new approach that learns a tri-modal video-gesture-speech-text representation to solve these tasks. By leveraging a combination of global phrase contrastive loss and local gesture-word coupling loss, we demonstrate that a strong gesture representation can be learned in a weakly supervised manner from videos in the wild. Our learned representations outperform previous methods, including large vision-language models (VLMs). Further analysis reveals that speech and text modalities capture distinct gesture related signals, underscoring the advantages of learning a shared tri-modal embedding space. The dataset, model, and code are available at: https://www.robots.ox.ac.uk/~vgg/research/jegal.

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the conditional distribution of semantic and acoustic features. Additionally, we leverage masked prediction as the training objective, enabling the model to generalize to other tasks such as music infilling and continuation in a zero-shot manner. Experiments on MusicCaps reveal that the music generated by MusicFlow exhibits superior quality and text coherence despite being over $2\sim5$ times smaller and requiring $5$ times fewer iterative steps. Simultaneously, the model can perform other music generation tasks and achieves competitive performance in music infilling and continuation.

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques on top of trivially pooled visual features. Instead, in this paper, we focus on the unique challenges encountered in lip reading and propose tailored solutions. To this end, we make the following contributions: (1) we propose an attention-based pooling mechanism to aggregate visual speech representations; (2) we use sub-word units for lip reading for the first time and show that this allows us to better model the ambiguities of the task; (3) we propose a model for Visual Speech Detection (VSD), trained on top of the lip reading network. Following the above, we obtain state-of-the-art results on the challenging LRS2 and LRS3 benchmarks when training on public datasets, and even surpass models trained on large-scale industrial datasets by using an order of magnitude less data. Our best model achieves 22.6% word error rate on the LRS2 dataset, a performance unprecedented for lip reading models, significantly reducing the performance gap between lip reading and automatic speech recognition. Moreover, on the AVA-ActiveSpeaker benchmark, our VSD model surpasses all visual-only baselines and even outperforms several recent audio-visual methods.

In this work, we address the problem of generating speech from silent lip videos for any speaker in the wild. In stark contrast to previous works, our method (i) is not restricted to a fixed number of speakers, (ii) does not explicitly impose constraints on the domain or the vocabulary and (iii) deals with videos that are recorded in the wild as opposed to within laboratory settings. The task presents a host of challenges, with the key one being that many features of the desired target speech, like voice, pitch and linguistic content, cannot be entirely inferred from the silent face video. In order to handle these stochastic variations, we propose a new VAE-GAN architecture that learns to associate the lip and speech sequences amidst the variations. With the help of multiple powerful discriminators that guide the training process, our generator learns to synthesize speech sequences in any voice for the lip movements of any person. Extensive experiments on multiple datasets show that we outperform all baselines by a large margin. Further, our network can be fine-tuned on videos of specific identities to achieve a performance comparable to single-speaker models that are trained on $4\times$ more data. We conduct numerous ablation studies to analyze the effect of different modules of our architecture. We also provide a demo video that demonstrates several qualitative results along with the code and trained models on our website http://cvit.iiit.ac.in/research/projects/cvit-projects/lip-to-speech-synthesis.

In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state- of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent works using lip movements as additional cues improve the quality of generated speech over "audio-only " methods. But, these methods cannot be used for several applications where the visual stream is unreliable or completely absent. We propose a new paradigm for speech enhancement by exploiting recent breakthroughs in speech- driven lip synthesis. Using one such model as a teacher network, we train a robust student network to produce accurate lip movements that mask away the noise, thus acting as a "visual noise filter". The intelligibility of the speech enhanced by our pseudo-lip approach is comparable ( <; 3% difference) to the case of using real lips. This implies that we can exploit the advantages of using lip movements even in the absence of a real video stream. We rigorously evaluate our model using quantitative metrics as well as human evaluations. Additional ablation studies and a demo video on our website containing qualitative comparisons and results clearly illustrate the effectiveness of our approach.

Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural speech given only the lip movements of a speaker. Acknowledging the importance of contextual and speaker-specific cues for accurate lip-reading, we take a different path from existing works. We focus on learning accurate lip sequences to speech mappings for individual speakers in unconstrained, large vocabulary settings. To this end, we collect and release a large-scale benchmark dataset, the first of its kind, specifically to train and evaluate the single-speaker lip to speech task in natural settings. We propose a novel approach with key design choices to achieve accurate, natural lip to speech synthesis in such unconstrained scenarios for the first time. Extensive evaluation using quantitative, qualitative metrics and human evaluation shows that our method is four times more intelligible than previous works in this space.

India is a country where several tens of languages are spoken by over a billion strong population. Text-to-speech systems for such languages will thus be extremely beneficial for wide-spread content creation and accessibility. Despite this, the current TTS systems for even the most popular Indian languages fall short of the contemporary state-of-the-art systems for English, Chinese, etc. We believe that one of the major reasons for this is the lack of large, publicly available text-to-speech corpora in these languages that are suitable for training neural text-to-speech systems. To mitigate this, we release a 24 hour text-to-speech corpus for 3 major Indian languages namely Hindi, Malayalam and Bengali. In this work, we also train a state-of-the-art TTS system for each of these languages and report their performances. The collected corpus, code, and trained models are made publicly available.

In this work, we investigate the problem of lip-syncing a talking face video of an arbitrary identity to match a target speech segment. Current works excel at producing accurate lip movements on a static image or videos of specific people seen during the training phase. However, they fail to accurately morph the lip movements of arbitrary identities in dynamic, unconstrained talking face videos, resulting in significant parts of the video being out-of-sync with the new audio. We identify key reasons pertaining to this and hence resolve them by learning from a powerful lip-sync discriminator. Next, we propose new, rigorous evaluation benchmarks and metrics to accurately measure lip synchronization in unconstrained videos. Extensive quantitative evaluations on our challenging benchmarks show that the lip-sync accuracy of the videos generated by our Wav2Lip model is almost as good as real synced videos. We provide a demo video clearly showing the substantial impact of our Wav2Lip model, and also publicly release the code, models, and evaluation benchmarks on our website.

In recent years, there has been an explosion in the number of memes being created and circulated in online social networks. Despite their rapidly increasing impact on how we communicate online, meme images are virtually inaccessible to the visually impaired users. Existing automated assistive systems that were primarily devised for natural photos in social media, overlook the specific fine-grained visual details in meme images. In this paper, we concentrate on describing one such prominent visual detail: the meme face emotion. We propose a novel automated method that enables visually impaired social media users to understand and appreciate meme face emotions with the help of rich textual captions. We first collect a challenging dataset of meme face emotion captions to support future research in face emotion understanding. We design a two-stage approach that significantly outperforms baseline approaches across all the standard captioning metrics and also generates richer discriminative captions. By validating our solution with the help of visually impaired social media users, we show that our emotion captions enable them to understand and appreciate one of the most popular classes of meme images encountered on the Internet for the first time. Code, data, and models are publicly available.

In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as "Face-to-Face Translation". As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization. In this work, we create an automatic pipeline for this problem and demonstrate its impact in multiple real-world applications. First, we build a working speech-to-speech translation system by bringing together multiple existing modules from speech and language. We then move towards "Face-to-Face Translation" by incorporating a novel visual module, LipGAN for generating realistic talking faces from the translated audio. Quantitative evaluation of LipGAN on the standard LRW test set shows that it significantly outperforms existing approaches across all standard metrics. We also subject our Face-to-Face Translation pipeline, to multiple human evaluations and show that it can significantly improve the overall user experience for consuming and interacting with multimodal content across languages. Code, models and demo video are made publicly available.