V2SFlow: Video-to-Speech Generation with Speech Decomposition and Rectified Flow

In this paper, we introduce V2SFlow, a novel Video-to-Speech (V2S) framework designed to generate natural and intelligible speech directly from silent talking face videos. While recent V2S systems have shown promising results on constrained datasets with limited speakers and vocabularies, their performance often degrades on real-world, unconstrained datasets due to the inherent variability and complexity of speech signals. To address these challenges, we decompose the speech signal into manageable subspaces (content, pitch, and speaker information), each representing distinct speech attributes, and predict them directly from the visual input. To generate coherent and realistic speech from these predicted attributes, we employ a rectified flow matching decoder built on a Transformer architecture, which models efficient probabilistic pathways from random noise to the target speech distribution. Extensive experiments demonstrate that V2SFlow significantly outperforms state-of-the-art methods, even surpassing the naturalness of ground truth utterances.

Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference without requiring additional training. Our core idea is to predict multiple tokens per inference step of the AR module using multiple prediction heads, resulting in a linear reduction in synthesis time as the number of heads increases. Furthermore, we introduce a novel speculative decoding technique that utilises a Viterbi-based algorithm to select the optimal sequence of generated tokens at each decoding step. In our experiments, we demonstrate that the time required to predict each token is reduced by a factor of 4 to 5 compared to baseline models, with minimal quality trade-off or even improvement in terms of speech intelligibility. Audio samples are available at: multpletokensprediction.github.io/multipletokensprediction.github.io/.

Text-To-Speech Synthesis In The Wild

Text-to-speech (TTS) systems are traditionally trained using modest databases of studio-quality, prompted or read speech collected in benign acoustic environments such as anechoic rooms. The recent literature nonetheless shows efforts to train TTS systems using data collected in the wild. While this approach allows for the use of massive quantities of natural speech, until now, there are no common datasets. We introduce the TTS In the Wild (TITW) dataset, the result of a fully automated pipeline, in this case, applied to the VoxCeleb1 dataset commonly used for speaker recognition. We further propose two training sets. TITW-Hard is derived from the transcription, segmentation, and selection of VoxCeleb1 source data. TITW-Easy is derived from the additional application of enhancement and additional data selection based on DNSMOS. We show that a number of recent TTS models can be trained successfully using TITW-Easy, but that it remains extremely challenging to produce similar results using TITW-Hard. Both the dataset and protocols are publicly available and support the benchmarking of TTS systems trained using TITW data.

VoxSim: A perceptual voice similarity dataset

This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and benchmarking of speaker similarity prediction models. We provide baseline results of speaker similarity prediction models on the VoxSim test set and further demonstrate that the model trained on our dataset generalises to the out-of-domain VCC2018 dataset.

FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is limited by slow inference speeds and computational complexity. To address this issue, we present FlowAVSE which enhances the inference speed and reduces the number of learnable parameters without degrading the output quality. In particular, we employ a conditional flow matching algorithm that enables the generation of high-quality speech in a single sampling step. Moreover, we increase efficiency by optimizing the underlying U-net architecture of diffusion-based systems. Our experiments demonstrate that FlowAVSE achieves 22 times faster inference speed and reduces the model size by half while maintaining the output quality. The demo page is available at: https://cyongong.github.io/FlowAVSE.github.io/

Faces that Speak: Jointly Synthesising Talking Face and Speech from Text

The goal of this work is to simultaneously generate natural talking faces and speech outputs from text. We achieve this by integrating Talking Face Generation (TFG) and Text-to-Speech (TTS) systems into a unified framework. We address the main challenges of each task: (1) generating a range of head poses representative of real-world scenarios, and (2) ensuring voice consistency despite variations in facial motion for the same identity. To tackle these issues, we introduce a motion sampler based on conditional flow matching, which is capable of high-quality motion code generation in an efficient way. Moreover, we introduce a novel conditioning method for the TTS system, which utilises motion-removed features from the TFG model to yield uniform speech outputs. Our extensive experiments demonstrate that our method effectively creates natural-looking talking faces and speech that accurately match the input text. To our knowledge, this is the first effort to build a multimodal synthesis system that can generalise to unseen identities.

FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder

The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes a complicated waveform into sub-band wavelets, which helps FreGrad to operate on a simple and concise feature space, (2) We design a frequency-aware dilated convolution that elevates frequency awareness, resulting in generating speech with accurate frequency information, and (3) We introduce a bag of tricks that boosts the generation quality of the proposed model. In our experiments, FreGrad achieves 3.7 times faster training time and 2.2 times faster inference speed compared to our baseline while reducing the model size by 0.6 times (only 1.78M parameters) without sacrificing the output quality. Audio samples are available at: https://mm.kaist.ac.kr/projects/FreGrad.

Let There Be Sound: Reconstructing High Quality Speech from Silent Videos

The goal of this work is to reconstruct high quality speech from lip motions alone, a task also known as lip-to-speech. A key challenge of lip-to-speech systems is the one-to-many mapping caused by (1) the existence of homophenes and (2) multiple speech variations, resulting in a mispronounced and over-smoothed speech. In this paper, we propose a novel lip-to-speech system that significantly improves the generation quality by alleviating the one-to-many mapping problem from multiple perspectives. Specifically, we incorporate (1) self-supervised speech representations to disambiguate homophenes, and (2) acoustic variance information to model diverse speech styles. Additionally, to better solve the aforementioned problem, we employ a flow based post-net which captures and refines the details of the generated speech. We perform extensive experiments and demonstrate that our method achieves the generation quality close to that of real human utterance, outperforming existing methods in terms of speech naturalness and intelligibility by a large margin. Synthesised samples are available at the anonymous demo page: https://mm.kaist.ac.kr/projects/LTBS.

CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis

While recent text-to-speech (TTS) systems have made remarkable strides toward human-level quality, the performance of cross-lingual TTS lags behind that of intra-lingual TTS. This gap is mainly rooted from the speaker-language entanglement problem in cross-lingual TTS. In this paper, we propose CrossSpeech which improves the quality of cross-lingual speech by effectively disentangling speaker and language information in the level of acoustic feature space. Specifically, CrossSpeech decomposes the speech generation pipeline into the speaker-independent generator (SIG) and speaker-dependent generator (SDG). The SIG produces the speaker-independent acoustic representation which is not biased to specific speaker distributions. On the other hand, the SDG models speaker-dependent speech variation that characterizes speaker attributes. By handling each information separately, CrossSpeech can obtain disentangled speaker and language representations. From the experiments, we verify that CrossSpeech achieves significant improvements in cross-lingual TTS, especially in terms of speaker similarity to the target speaker.

Relation-aware Language-Graph Transformer for Question Answering

Question Answering (QA) is a task that entails reasoning over natural language contexts, and many relevant works augment language models (LMs) with graph neural networks (GNNs) to encode the Knowledge Graph (KG) information. However, most existing GNN-based modules for QA do not take advantage of rich relational information of KGs and depend on limited information interaction between the LM and the KG. To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner. Specifically, QAT constructs Meta-Path tokens, which learn relation-centric embeddings based on diverse structural and semantic relations. Then, our Relation-Aware Self-Attention module comprehensively integrates different modalities via the Cross-Modal Relative Position Bias, which guides information exchange between relevant entities of different modalities. We validate the effectiveness of QAT on commonsense question answering datasets like CommonsenseQA and OpenBookQA, and on a medical question answering dataset, MedQA-USMLE. On all the datasets, our method achieves state-of-the-art performance. Our code is available at http://github.com/mlvlab/QAT.