MM-TTS: A Unified Framework for Multimodal, Prompt-Induced Emotional Text-to-Speech Synthesis
- URL: http://arxiv.org/abs/2404.18398v1
- Date: Mon, 29 Apr 2024 03:19:39 GMT
- Title: MM-TTS: A Unified Framework for Multimodal, Prompt-Induced Emotional Text-to-Speech Synthesis
- Authors: Xiang Li, Zhi-Qi Cheng, Jun-Yan He, Xiaojiang Peng, Alexander G. Hauptmann,
- Abstract summary: 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.
- Score: 70.06396781553191
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Emotional Text-to-Speech (E-TTS) synthesis has gained significant attention in recent years due to its potential to enhance human-computer interaction. However, current E-TTS approaches often struggle to capture the complexity of human emotions, primarily relying on oversimplified emotional labels or single-modality inputs. To address these limitations, we propose the Multimodal Emotional Text-to-Speech System (MM-TTS), 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: (1) the Emotion Prompt Alignment Module (EP-Align), which employs contrastive learning to align emotional features across text, audio, and visual modalities, ensuring a coherent fusion of multimodal information; and (2) 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. Extensive evaluations across diverse datasets demonstrate the superior performance of MM-TTS compared to traditional E-TTS models. Objective metrics, including Word Error Rate (WER) and Character Error Rate (CER), show significant improvements on ESD dataset, with MM-TTS achieving scores of 7.35% and 3.07%, respectively. Subjective assessments further validate that MM-TTS generates speech with emotional fidelity and naturalness comparable to human speech. Our code and pre-trained models are publicly available at https://anonymous.4open.science/r/MMTTS-D214
Related papers
- Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content [56.62027582702816]
Multimodal Sentiment Analysis seeks to unravel human emotions by amalgamating text, audio, and visual data.
Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge.
We introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions.
arXiv Detail & Related papers (2024-12-12T11:30:41Z) - Making Social Platforms Accessible: Emotion-Aware Speech Generation with Integrated Text Analysis [3.8251125989631674]
We propose an end-to-end context-aware Text-to-Speech (TTS) synthesis system.
It derives the conveyed emotion from text input and synthesises audio that focuses on emotions and speaker features for natural and expressive speech.
Our system showcases competitive inference time performance when benchmarked against state-of-the-art TTS models.
arXiv Detail & Related papers (2024-10-24T23:18:02Z) - 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) - Facial Expression-Enhanced TTS: Combining Face Representation and Emotion Intensity for Adaptive Speech [0.13654846342364302]
FEIM-TTS is a zero-shot text-to-speech model that synthesizes emotionally expressive speech aligned with facial images.
The model is trained using LRS3, CREMA-D, and MELD datasets, demonstrating its adaptability.
By integrating emotional nuances into TTS, our model enables dynamic and engaging auditory experiences for webcomics, allowing visually impaired users to enjoy these narratives more fully.
arXiv Detail & Related papers (2024-09-24T16:01:12Z) - Attention-based Interactive Disentangling Network for Instance-level
Emotional Voice Conversion [81.1492897350032]
Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components.
We propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion.
arXiv Detail & Related papers (2023-12-29T08:06:45Z) - 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) - Reinforcement Learning for Emotional Text-to-Speech Synthesis with
Improved Emotion Discriminability [82.39099867188547]
Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years.
We propose a new interactive training paradigm for ETTS, denoted as i-ETTS.
We formulate an iterative training strategy with reinforcement learning to ensure the quality of i-ETTS optimization.
arXiv Detail & Related papers (2021-04-03T13:52:47Z) - 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.