English
Related papers

Related papers: Generating diverse and natural text-to-speech samp…

200 papers

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…

Computation and Language · Computer Science 2021-11-16 Zhu Li , Yuqing Zhang , Mengxi Nie , Ming Yan , Mengnan He , Ruixiong Zhang , Caixia Gong

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

Machine Learning · Computer Science 2020-06-01 Partha Ghosh , Mehdi S. M. Sajjadi , Antonio Vergari , Michael Black , Bernhard Schölkopf

Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time…

Sound · Computer Science 2024-06-06 Po-chun Hsu , Da-rong Liu , Andy T. Liu , Hung-yi Lee

While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-26 Wangzixi Zhou , Bagus Tris Atmaja , Sakriani Sakti

This paper proposes a hierarchical and multi-scale variational autoencoder-based non-autoregressive text-to-speech model (HiMuV-TTS) to generate natural speech with diverse speaking styles. Recent advances in non-autoregressive TTS…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-16 Jae-Sung Bae , Jinhyeok Yang , Tae-Jun Bak , Young-Sun Joo

Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In response, we present the Cross-Utterance Conditioned…

Sound · Computer Science 2024-09-20 Yang Li , Cheng Yu , Guangzhi Sun , Weiqin Zu , Zheng Tian , Ying Wen , Wei Pan , Chao Zhang , Jun Wang , Yang Yang , Fanglei Sun

In voice conversion (VC), an approach showing promising results in the latest voice conversion challenge (VCC) 2020 is to first use an automatic speech recognition (ASR) model to transcribe the source speech into the underlying linguistic…

Sound · Computer Science 2021-07-21 Wen-Chin Huang , Tomoki Hayashi , Xinjian Li , Shinji Watanabe , Tomoki Toda

Wasserstein autoencoders are effective for text generation. They do not however provide any control over the style and topic of the generated sentences if the dataset has multiple classes and includes different topics. In this work, we…

Computation and Language · Computer Science 2019-11-12 Amirpasha Ghabussi , Lili Mou , Olga Vechtomova

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

Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in…

Machine Learning · Computer Science 2023-12-13 Julia Huiming Wang , Dexter Tsin , Tatiana Engel

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

Machine Learning · Computer Science 2018-05-31 Aaron van den Oord , Oriol Vinyals , Koray Kavukcuoglu

Recently, a variational autoencoder (VAE)-based single-channel speech enhancement system using Bayesian permutation training has been proposed, which uses two pretrained VAEs to obtain latent representations for speech and noise. Based on…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-03 Jiatong Li , Simon Doclo

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-31 Kai Shen , Zeqian Ju , Xu Tan , Yanqing Liu , Yichong Leng , Lei He , Tao Qin , Sheng Zhao , Jiang Bian

Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Devang S Ram Mohan , Vivian Hu , Tian Huey Teh , Alexandra Torresquintero , Christopher G. R. Wallis , Marlene Staib , Lorenzo Foglianti , Jiameng Gao , Simon King

Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as personalized voice assistant services. While several approaches have been proposed, they often exhibit high…

Sound · Computer Science 2024-12-31 Wooseok Han , Minki Kang , Changhun Kim , Eunho Yang

Many speech enhancement (SE) methods rely on continuous representations. Recently, discrete audio tokens have been explored to enable autoregressive generation for SE. However, it remains unclear whether discretization itself consistently…

Sound · Computer Science 2026-03-24 Jingyi Li , Luca Della Libera , Mirco Ravanelli , Cem Subakan

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

Sound · Computer Science 2024-10-07 Olga Iakovenko , Ivan Bondarenko

Generally speaking, the main objective when training a neural speech synthesis system is to synthesize natural and expressive speech from the output layer of the neural network without much attention given to the hidden layers. However, by…

Sound · Computer Science 2021-06-28 Hieu-Thi Luong , Junichi Yamagishi

Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic…

Computation and Language · Computer Science 2021-04-21 Shubhi Tyagi , Marco Nicolis , Jonas Rohnke , Thomas Drugman , Jaime Lorenzo-Trueba

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Computation and Language · Computer Science 2026-04-07 Oshri Naparstek