Emotional Face-to-Speech

• URL: http://arxiv.org/abs/2502.01046v1
• Date: Mon, 03 Feb 2025 04:48:50 GMT
• Title: Emotional Face-to-Speech
• Authors: Jiaxin Ye, Boyuan Cao, Hongming Shan,
• Abstract summary: Existing face-to-speech methods offer great promise in capturing identity characteristics but struggle to generate diverse vocal styles with emotional expression. We introduce DEmoFace, a novel generative framework that leverages a discrete diffusion transformer (DiT) with curriculum learning. We develop an enhanced predictor-free guidance to handle diverse conditioning scenarios, enabling multi-conditional generation and disentangling complex attributes effectively.
• Score: 13.725558939494407
• License:
• Abstract: How much can we infer about an emotional voice solely from an expressive face? This intriguing question holds great potential for applications such as virtual character dubbing and aiding individuals with expressive language disorders. Existing face-to-speech methods offer great promise in capturing identity characteristics but struggle to generate diverse vocal styles with emotional expression. In this paper, we explore a new task, termed emotional face-to-speech, aiming to synthesize emotional speech directly from expressive facial cues. To that end, we introduce DEmoFace, a novel generative framework that leverages a discrete diffusion transformer (DiT) with curriculum learning, built upon a multi-level neural audio codec. Specifically, we propose multimodal DiT blocks to dynamically align text and speech while tailoring vocal styles based on facial emotion and identity. To enhance training efficiency and generation quality, we further introduce a coarse-to-fine curriculum learning algorithm for multi-level token processing. In addition, we develop an enhanced predictor-free guidance to handle diverse conditioning scenarios, enabling multi-conditional generation and disentangling complex attributes effectively. Extensive experimental results demonstrate that DEmoFace generates more natural and consistent speech compared to baselines, even surpassing speech-driven methods. Demos are shown at https://demoface-ai.github.io/.

Related papers

• FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles [29.185409608539747]
  Vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces. We introduce a novel FaceSpeak approach, which extracts salient identity characteristics and emotional representations from a wide variety of image styles. It mitigates the extraneous information, resulting in synthesized speech closely aligned with a character's persona.
  arXiv  Detail & Related papers  (2025-01-02T02:00:15Z)
• DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation [14.07086606183356]
  Speech-driven 3D facial animation has garnered lots of attention thanks to its broad range of applications. Current methods fail to capture the nuanced emotional undertones conveyed through speech and produce monotonous facial motion. We introduce DEEPTalk, a novel approach that generates diverse and emotionally rich 3D facial expressions directly from speech inputs.
  arXiv  Detail & Related papers  (2024-08-12T08:56:49Z)
• Emotional Listener Portrait: Realistic Listener Motion Simulation in Conversation [50.35367785674921]
  Listener head generation centers on generating non-verbal behaviors of a listener in reference to the information delivered by a speaker. A significant challenge when generating such responses is the non-deterministic nature of fine-grained facial expressions during a conversation. We propose the Emotional Listener Portrait (ELP), which treats each fine-grained facial motion as a composition of several discrete motion-codewords. Our ELP model can not only automatically generate natural and diverse responses toward a given speaker via sampling from the learned distribution but also generate controllable responses with a predetermined attitude.
  arXiv  Detail & Related papers  (2023-09-29T18:18:32Z)
• ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models [83.07390037152963]
  ZET-Speech is a zero-shot adaptive emotion-controllable TTS model. It allows users to synthesize any speaker's emotional speech using only a short, neutral speech segment and the target emotion label. Experimental results demonstrate that ZET-Speech successfully synthesizes natural and emotional speech with the desired emotion for both seen and unseen speakers.
  arXiv  Detail & Related papers  (2023-05-23T08:52:00Z)
• High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning [43.09015109281053]
  We propose a more flexible and generalized framework for talking face generation. Specifically, we supplement the emotion style in text prompts and use an Aligned Multi-modal Emotion encoder to embed the text, image, and audio emotion modality into a unified space. An Emotion-aware Audio-to-3DMM Convertor is proposed to connect the emotion condition and the audio sequence to structural representation.
  arXiv  Detail & Related papers  (2023-05-04T05:59:34Z)
• Emotionally Enhanced Talking Face Generation [52.07451348895041]
  We build a talking face generation framework conditioned on a categorical emotion to generate videos with appropriate expressions. We show that our model can adapt to arbitrary identities, emotions, and languages. Our proposed framework is equipped with a user-friendly web interface with a real-time experience for talking face generation with emotions.
  arXiv  Detail & Related papers  (2023-03-21T02:33:27Z)
• FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning [0.0]
  FaceXHuBERT is a text-less speech-driven 3D facial animation generation method. It is very robust to background noise and can handle audio recorded in a variety of situations. It produces superior results with respect to the realism of the animation 78% of the time.
  arXiv  Detail & Related papers  (2023-03-09T17:05:19Z)
• 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)
• EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model [56.75775793011719]
  We introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. Unlike those models which need additional reference audio as input, our model could predict emotion labels just from the input text and generate more expressive speech conditioned on the emotion embedding. In the experiment phase, we first validate the effectiveness of our dataset by an emotion classification task. Then we train our model on the proposed dataset and conduct a series of subjective evaluations.
  arXiv  Detail & Related papers  (2021-06-17T08:34:21Z)
• Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training [91.95855310211176]
  Emotional voice conversion aims to change the emotional state of an utterance while preserving the linguistic content and speaker identity. We propose a novel 2-stage training strategy for sequence-to-sequence emotional voice conversion with a limited amount of emotional speech data. The proposed framework can perform both spectrum and prosody conversion and achieves significant improvement over the state-of-the-art baselines in both objective and subjective evaluation.
  arXiv  Detail & Related papers  (2021-03-31T04:56:14Z)
• Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset [84.53659233967225]
  Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. We propose a novel framework based on variational auto-encoding Wasserstein generative adversarial network (VAW-GAN) We show that the proposed framework achieves remarkable performance by consistently outperforming the baseline framework.
  arXiv  Detail & Related papers  (2020-10-28T07:16:18Z)

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.