Lip-to-speech involves generating a natural-sounding speech synchronized with a soundless video of a person talking. Despite recent advances, current methods still cannot produce high-quality speech with high levels of intelligibility for challenging and realistic datasets such as LRS3. In this work, we present LipVoicer, a novel method that generates high-quality speech, even for in-the-wild and rich datasets, by incorporating the text modality. Given a silent video, we first predict the spoken text using a pre-trained lip-reading network. We then condition a diffusion model on the video and use the extracted text through a classifier-guidance mechanism where a pre-trained automatic speech recognition (ASR ) serves as the classifier. LipVoicer outperforms multiple lip-to-speech baselines on LRS2 and LRS3, which are in-the-wild datasets with hundreds of unique speakers in their test set and an unrestricted vocabulary. Moreover, our experiments show that the inclusion of the text modality plays a major role in the intelligibility of the produced speech, readily perceptible while listening, and is empirically reflected in the substantial reduction of the word error rate ( WER ) metric. We demonstrate the effectiveness of LipVoicer through human evaluation, which shows that it produces more natural and synchronized speech signals compared to competing methods. Finally, we created a demo showcasing LipVoicer’s superiority in producing natural, synchronized, and intelligible speech, providing additional evidence of its effectiveness. Project page and code: https://github.com/yochaiye/LipVoicer

Gaussian processes (GPs) are non-parametric, flexible, models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning (DKL) is especially compelling due to the strong representational power induced by the network. However, inference in GPs, whether with or without DKL, can be computationally challenging on large datasets. Here, we propose GP-Tree, a novel method for multi-class classification with Gaussian processes and DKL. We develop a tree-based hierarchical model in which each internal node of the tree fits a GP to the data using the P{ó}lya-Gamma augmentation scheme. As a result, our method scales well with both the number of classes and data size. We demonstrate the effectiveness of our method against other Gaussian process training baselines, and we show how our general GP approach achieves improved accuracy on standard incremental few-shot learning benchmarks.

Neural networks (NNs) have been widely applied in speech processing tasks, and, in particular, those employing microphone arrays. Nevertheless, most existing NN architectures can only deal with fixed and position-specific microphone arrays. In this paper, we present an NN architecture that can cope with microphone arrays whose number and positions of the microphones are unknown, and demonstrate its applicability in the speech dereverberation task. To this end, our approach harnesses recent advances in deep learning on set-structured data to design an architecture that enhances the reverberant log-spectrum. We use noisy and noiseless versions of a simulated reverberant dataset to test the proposed architecture. Our experiments on the noisy data show that the proposed scene-agnostic setup outperforms a powerful scene-aware framework, sometimes even with fewer microphones. With the noiseless dataset we show that, in most cases, our method outperforms the position-aware network as well as the state-of-the-art weighted linear prediction error (WPE) algorithm.

In speech enhancement, the use of supervised algorithms in the form of deep neural networks (DNNs) has become tremendously popular in recent years. The target function of the DNN (and the associated estimators) is often either a masking function applied to the noisy spectrum, or the clean log-spectrum. In this work, we show that both separate cost functions are unsuitable for dealing with narrowband noise, and propose a new composite estimator in the log-spectrum domain. The new technique relies on a single DNN that outputs both a masking function and an estimated log-spectrum. Both outputs are used for the composite enhancement. The proposed estimator demonstrates superior performance for speech utterances contaminated by additive narrowband noise, while maintaining the enhancement quality of the baseline algorithms for wideband noise.