English
Related papers

Related papers: EmoMix: Emotion Mixing via Diffusion Models for Em…

200 papers

Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks. However, emotional speech samples are more difficult and expensive to acquire compared with Neutral…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Shijun Wang , Jón Guðnason , Damian Borth

While recent advances in Text-to-Speech (TTS) technology produce natural and expressive speech, they lack the option for users to select emotion and control intensity. We propose EmoKnob, a framework that allows fine-grained emotion control…

Computation and Language · Computer Science 2024-10-02 Haozhe Chen , Run Chen , Julia Hirschberg

We often verbally express emotions in a multifaceted manner, they may vary in their intensities and may be expressed not just as a single but as a mixture of emotions. This wide spectrum of emotions is well-studied in the structural model…

Computation and Language · Computer Science 2024-06-28 Rendi Chevi , Alham Fikri Aji

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…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-18 Haibin Wu , Xiaofei Wang , Sefik Emre Eskimez , Manthan Thakker , Daniel Tompkins , Chung-Hsien Tsai , Canrun Li , Zhen Xiao , Sheng Zhao , Jinyu Li , Naoyuki Kanda

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Sound · Computer Science 2024-04-02 Xiang Li , Fan Bu , Ambuj Mehrish , Yingting Li , Jiale Han , Bo Cheng , Soujanya Poria

Emotional voice conversion (EVC) traditionally targets the transformation of spoken utterances from one emotional state to another, with previous research mainly focusing on discrete emotion categories. This paper departs from the norm by…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Kun Zhou , Berrak Sisman , Carlos Busso , Bin Ma , Haizhou Li

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

In this paper, we propose to utilise diffusion models for data augmentation in speech emotion recognition (SER). In particular, we present an effective approach to utilise improved denoising diffusion probabilistic models (IDDPM) to…

Sound · Computer Science 2023-05-22 Ibrahim Malik , Siddique Latif , Raja Jurdak , Björn Schuller

While the performance of cross-lingual TTS based on monolingual corpora has been significantly improved recently, generating cross-lingual speech still suffers from the foreign accent problem, leading to limited naturalness. Besides,…

Sound · Computer Science 2023-09-06 Tao Li , Chenxu Hu , Jian Cong , Xinfa Zhu , Jingbei Li , Qiao Tian , Yuping Wang , Lei Xie

Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotion-Aware Stepwise…

Computation and Language · Computer Science 2026-02-10 Jiacheng Shi , Hongfei Du , Yangfan He , Y. Alicia Hong , Ye Gao

In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS. First, we investigated…

Computation and Language · Computer Science 2024-10-28 Ziyang Ma , Wen Wu , Zhisheng Zheng , Yiwei Guo , Qian Chen , Shiliang Zhang , Xie Chen

Learning emotion embedding from reference audio is a straightforward approach for multi-emotion speech synthesis in encoder-decoder systems. But how to get better emotion embedding and how to inject it into TTS acoustic model more…

Sound · Computer Science 2022-01-31 Fengyu Yang , Jian Luan , Yujun Wang

Expressive Text-to-Speech (TTS) using reference speech has been studied extensively to synthesize natural speech, but there are limitations to obtaining well-represented styles and improving model generalization ability. In this study, we…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-28 Hyun Joon Park , Jin Sob Kim , Wooseok Shin , Sung Won Han

Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-10 Sarath Sivaprasad , Saiteja Kosgi , Vineet Gandhi

We present a methodology to train our multi-speaker emotional text-to-speech synthesizer that can express speech for 10 speakers' 7 different emotions. All silences from audio samples are removed prior to learning. This results in fast…

Computation and Language · Computer Science 2021-12-08 Sungjae Cho , Soo-Young Lee

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

Sound · Computer Science 2023-06-27 Dongchao Yang , Songxiang Liu , Rongjie Huang , Chao Weng , Helen Meng

Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Guanwen Feng , Haoran Cheng , Yunan Li , Zhiyuan Ma , Chaoneng Li , Zhihao Qian , Qiguang Miao , Chi-Man Pun

This paper introduces EmoSSLSphere, a novel framework for multilingual emotional text-to-speech (TTS) synthesis that combines spherical emotion vectors with discrete token features derived from self-supervised learning (SSL). By encoding…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Joonyong Park , Kenichi Nakamura

In recent years, prompting has quickly become one of the standard ways of steering the outputs of generative machine learning models, due to its intuitive use of natural language. In this work, we propose a system conditioned on embeddings…

Computation and Language · Computer Science 2024-06-13 Thomas Bott , Florian Lux , Ngoc Thang Vu

We propose FEIM-TTS, an innovative zero-shot text-to-speech (TTS) model that synthesizes emotionally expressive speech, aligned with facial images and modulated by emotion intensity. Leveraging deep learning, FEIM-TTS transcends traditional…

Sound · Computer Science 2024-09-25 Yunji Chu , Yunseob Shim , Unsang Park