Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech

• URL: http://arxiv.org/abs/2407.12229v2
• Date: Tue, 17 Sep 2024 10:40:11 GMT
• Title: Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech
• Authors: Haibin Wu, Xiaofei Wang, Sefik Emre Eskimez, Manthan Thakker, Daniel Tompkins, Chung-Hsien Tsai, Canrun Li, Zhen Xiao, Sheng Zhao, Jinyu Li, Naoyuki Kanda,
• Abstract summary: EmoCtrl-TTS is an emotion-controllable zero-shot TTS that can generate highly emotional speech with NVs for any speaker. To achieve high-quality emotional speech generation, EmoCtrl-TTS is trained using more than 27,000 hours of expressive data curated based on pseudo-labeling.
• Score: 51.486112860259595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich emotions, including NVs. This paper introduces EmoCtrl-TTS, an emotion-controllable zero-shot TTS that can generate highly emotional speech with NVs for any speaker. EmoCtrl-TTS leverages arousal and valence values, as well as laughter embeddings, to condition the flow-matching-based zero-shot TTS. To achieve high-quality emotional speech generation, EmoCtrl-TTS is trained using more than 27,000 hours of expressive data curated based on pseudo-labeling. Comprehensive evaluations demonstrate that EmoCtrl-TTS excels in mimicking the emotions of audio prompts in speech-to-speech translation scenarios. We also show that EmoCtrl-TTS can capture emotion changes, express strong emotions, and generate various NVs in zero-shot TTS. See https://aka.ms/emoctrl-tts for demo samples.

Related papers

• Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions [37.075331767703986]
  Current emotional text-to-speech systems face challenges in mimicking a broad spectrum of human emotions. This paper proposes a TTS framework that facilitates control over pleasure, arousal, and dominance. It can synthesize a diversity of emotional styles without requiring any emotional speech data during TTS training.
  arXiv  Detail & Related papers  (2024-09-25T07:16:16Z)
• MM-TTS: A Unified Framework for Multimodal, Prompt-Induced Emotional Text-to-Speech Synthesis [70.06396781553191]
  Multimodal Emotional Text-to-Speech System (MM-TTS) is a unified framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. MM-TTS consists of two key components: the Emotion Prompt Alignment Module (EP-Align), which employs contrastive learning to align emotional features across text, audio, and visual modalities, and the Emotion Embedding-Induced TTS (EMI-TTS), which integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions.
  arXiv  Detail & Related papers  (2024-04-29T03:19:39Z)
• Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like [49.2096391012794]
  ELaTE is a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt. We develop our model based on the foundation of conditional flow-matching-based zero-shot TTS. We show that ELaTE can generate laughing speech with significantly higher quality and controllability compared to conventional models.
  arXiv  Detail & Related papers  (2024-02-12T02:58:10Z)
• 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)
• Fine-grained Emotional Control of Text-To-Speech: Learning To Rank Inter- And Intra-Class Emotion Intensities [1.4986031916712106]
  State-of-the-art Text-To-Speech (TTS) models are capable of producing high-quality speech. We propose a fine-grained controllable emotional TTS, that considers both inter- and intra-class distances. Our experiments demonstrate that our model exceeds two state-of-the-art controllable TTS models for controllability, emotion and naturalness.
  arXiv  Detail & Related papers  (2023-03-02T09:09:03Z)
• Emotional Prosody Control for Speech Generation [7.66200737962746]
  We propose a text to speech(TTS) system, where a user can choose the emotion of generated speech from a continuous and meaningful emotion space. The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion.
  arXiv  Detail & Related papers  (2021-11-07T08:52:04Z)
• 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)

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.