From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech

• URL: http://arxiv.org/abs/2503.16956v1
• Date: Fri, 21 Mar 2025 09:02:38 GMT
• Title: From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
• Authors: Ji-Hoon Kim, Jeongsoo Choi, Jaehun Kim, Chaeyoung Jung, Joon Son Chung,
• Abstract summary: The objective of this study is to generate high-quality speech from silent talking face videos.<n>We propose a novel video-to-speech system that bridges the modality gap between silent video and multi-faceted speech.<n>Our method achieves exceptional generation quality comparable to real utterances.
• Score: 26.67378997911053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The objective of this study is to generate high-quality speech from silent talking face videos, a task also known as video-to-speech synthesis. A significant challenge in video-to-speech synthesis lies in the substantial modality gap between silent video and multi-faceted speech. In this paper, we propose a novel video-to-speech system that effectively bridges this modality gap, significantly enhancing the quality of synthesized speech. This is achieved by learning of hierarchical representations from video to speech. Specifically, we gradually transform silent video into acoustic feature spaces through three sequential stages -- content, timbre, and prosody modeling. In each stage, we align visual factors -- lip movements, face identity, and facial expressions -- with corresponding acoustic counterparts to ensure the seamless transformation. Additionally, to generate realistic and coherent speech from the visual representations, we employ a flow matching model that estimates direct trajectories from a simple prior distribution to the target speech distribution. Extensive experiments demonstrate that our method achieves exceptional generation quality comparable to real utterances, outperforming existing methods by a significant margin.

Related papers

• Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers [58.86974149731874]
  Cosh-DiT is a Co-speech gesture video system with hybrid Diffusion Transformers.<n>We introduce an audio Diffusion Transformer to synthesize expressive gesture dynamics synchronized with speech rhythms.<n>For realistic video synthesis conditioned on the generated speech-driven motion, we design a visual Diffusion Transformer.
  arXiv  Detail & Related papers  (2025-03-13T01:36:05Z)
• SpeechX: Neural Codec Language Model as a Versatile Speech Transformer [57.82364057872905]
  SpeechX is a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks. Experimental results show SpeechX's efficacy in various tasks, including zero-shot TTS, noise suppression, target speaker extraction, speech removal, and speech editing with or without background noise.
  arXiv  Detail & Related papers  (2023-08-14T01:01:19Z)
• Learning to Dub Movies via Hierarchical Prosody Models [167.6465354313349]
  Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. We propose a novel movie dubbing architecture to tackle these problems via hierarchical prosody modelling, which bridges the visual information to corresponding speech prosody from three aspects: lip, face, and scene.
  arXiv  Detail & Related papers  (2022-12-08T03:29:04Z)
• VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection [32.65865343643458]
  Recent studies have shown impressive performance on synthesizing speech from silent talking face videos. We introduce speech-visage selection module that separates the speech content and the speaker identity from the visual features of the input video. Proposed framework brings the advantage of synthesizing the speech containing the right content even when the silent talking face video of an unseen subject is given.
  arXiv  Detail & Related papers  (2022-06-15T11:29:58Z)
• Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis [67.73554826428762]
  We propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech, enabling efficient synthesis of clean, realistic speech from noisy signals.
  arXiv  Detail & Related papers  (2022-03-31T17:57:10Z)
• Speech2Video: Cross-Modal Distillation for Speech to Video Generation [21.757776580641902]
  Speech-to-video generation technique can spark interesting applications in entertainment, customer service, and human-computer-interaction industries. The challenge mainly lies in disentangling the distinct visual attributes from audio signals. We propose a light-weight, cross-modal distillation method to extract disentangled emotional and identity information from unlabelled video inputs.
  arXiv  Detail & Related papers  (2021-07-10T10:27:26Z)
• Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation [28.157431757281692]
  We propose a text-based talking-head video generation framework that synthesizes high-fidelity facial expressions and head motions. Our framework consists of a speaker-independent stage and a speaker-specific stage. Our algorithm achieves high-quality photo-realistic talking-head videos including various facial expressions and head motions according to speech rhythms.
  arXiv  Detail & Related papers  (2021-04-16T09:44:12Z)
• VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency [111.55430893354769]
  Given a video, the goal is to extract the speech associated with a face in spite of simultaneous background sounds and/or other human speakers. Our approach jointly learns audio-visual speech separation and cross-modal speaker embeddings from unlabeled video. It yields state-of-the-art results on five benchmark datasets for audio-visual speech separation and enhancement.
  arXiv  Detail & Related papers  (2021-01-08T18:25:24Z)
• Vocoder-Based Speech Synthesis from Silent Videos [28.94460283719776]
  We present a way to synthesise speech from the silent video of a talker using deep learning. The system learns a mapping function from raw video frames to acoustic features and reconstructs the speech with a vocoder synthesis algorithm.
  arXiv  Detail & Related papers  (2020-04-06T10:22:04Z)
• Visually Guided Self Supervised Learning of Speech Representations [62.23736312957182]
  We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. We achieve state of the art results for emotion recognition and competitive results for speech recognition.
  arXiv  Detail & Related papers  (2020-01-13T14:53:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.