English
Related papers

Related papers: Varianceflow: High-Quality and Controllable Text-t…

200 papers

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the…

Sound · Computer Science 2023-09-01 Weiqin Li , Shun Lei , Qiaochu Huang , Yixuan Zhou , Zhiyong Wu , Shiyin Kang , Helen Meng

Recently normalizing flows have been gaining traction in text-to-speech (TTS) and voice conversion (VC) due to their state-of-the-art (SOTA) performance. Normalizing flows are unsupervised generative models. In this paper, we introduce…

Sound · Computer Science 2023-12-29 Jakub Mosiński , Piotr Biliński , Thomas Merritt , Abdelhamid Ezzerg , Daniel Korzekwa

We propose a novel description-based controllable text-to-speech (TTS) method with cross-lingual control capability. To address the lack of audio-description paired data in the target language, we combine a TTS model trained on the target…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Ryuichi Yamamoto , Yuma Shirahata , Masaya Kawamura , Kentaro Tachibana

Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Ryan Burgert , Yuancheng Xu , Wenqi Xian , Oliver Pilarski , Pascal Clausen , Mingming He , Li Ma , Yitong Deng , Lingxiao Li , Mohsen Mousavi , Michael Ryoo , Paul Debevec , Ning Yu

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

Normalizing flows are a powerful class of generative models for continuous random variables, showing both strong model flexibility and the potential for non-autoregressive generation. These benefits are also desired when modeling discrete…

Machine Learning · Statistics 2019-06-06 Zachary M. Ziegler , Alexander M. Rush

Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-30 Taejun Bak , Jae-Sung Bae , Hanbin Bae , Young-Ik Kim , Hoon-Young Cho

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

Sound · Computer Science 2025-10-06 Hieu-Nghia Huynh-Nguyen , Huynh Nguyen Dang , Ngoc-Son Nguyen , Van Nguyen

Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces…

Sound · Computer Science 2022-07-14 Zhengxi Liu , Qiao Tian , Chenxu Hu , Xudong Liu , Menglin Wu , Yuping Wang , Hang Zhao , Yuxuan Wang

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

This paper proposes a novel voice conversion (VC) method based on non-autoregressive sequence-to-sequence (NAR-S2S) models. Inspired by the great success of NAR-S2S models such as FastSpeech in text-to-speech (TTS), we extend the…

Sound · Computer Science 2021-04-15 Tomoki Hayashi , Wen-Chin Huang , Kazuhiro Kobayashi , Tomoki Toda

This paper explores multi-modal controllable Text-to-Speech Synthesis (TTS) where the voice can be generated from face image, and the characteristics of output speech (e.g., pace, noise level, distance, tone, place) can be controllable with…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-27 Minsu Kim , Pingchuan Ma , Honglie Chen , Stavros Petridis , Maja Pantic

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

Computation and Language · Computer Science 2017-10-31 Bin Wang , Zhijian Ou

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Sound · Computer Science 2021-06-22 Mohammed Salah Al-Radhi , Tamás Gábor Csapó , Géza Németh

This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to…

Audio and Speech Processing · Electrical Eng. & Systems 2018-03-07 Md Tauhidul Islam , Celia Shahnaz

Large language models show that simple autoregressive training can yield scalable and coherent generation, but extending this paradigm to speech remains challenging due to the entanglement of semantic and acoustic information. Most existing…

Machine Learning · Computer Science 2026-03-06 Luca Della Libera , Cem Subakan , Mirco Ravanelli

The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo…

Machine Learning · Statistics 2020-10-27 Hao Wu , Jonas Köhler , Frank Noé

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-18 Daning Zhang , Ying Wei

Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply…

Computation and Language · Computer Science 2026-05-21 Chanhyuk Lee , Jaehoon Yoo , Manan Agarwal , Sheel Shah , Jerry Huang , Aditi Raghunathan , Seunghoon Hong , Nicholas M. Boffi , Jinwoo Kim

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Sound · Computer Science 2023-09-14 Zhichao Wu , Qiulin Li , Sixing Liu , Qun Yang