English
Related papers

Related papers: Learning in your voice: Non-parallel voice convers…

200 papers

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-12 Janek Ebbers , Michael Kuhlmann , Tobias Cord-Landwehr , Reinhold Haeb-Umbach

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

Sound · Computer Science 2026-04-02 Xiaoxu Zhu , Junhua Li , Aaron J. Li , Guangchao Yao , Xiaojie Yu

In this paper, a novel Convolutional Neural Network architecture has been developed for speaker verification in order to simultaneously capture and discard speaker and non-speaker information, respectively. In training phase, the network is…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-13 Hossein Salehghaffari

Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-21 Zexin Cai , Henry Li Xinyuan , Ashi Garg , Leibny Paola García-Perera , Kevin Duh , Sanjeev Khudanpur , Matthew Wiesner , Nicholas Andrews

One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-02 Yinghao Aaron Li , Cong Han , Nima Mesgarani

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Siyuan Feng , Tan Lee , Zhiyuan Peng

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…

Computation and Language · Computer Science 2025-07-22 Varun Krishna , Sriram Ganapathy

Recently, voice conversion (VC) has been widely studied. Many VC systems use disentangle-based learning techniques to separate the speaker and the linguistic content information from a speech signal. Subsequently, they convert the voice by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 Yen-Hao Chen , Da-Yi Wu , Tsung-Han Wu , Hung-yi Lee

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-14 Yusuf Brima , Ulf Krumnack , Simone Pika , Gunther Heidemann

Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a…

Sound · Computer Science 2023-03-01 Dianwen Ng , Ruixi Zhang , Jia Qi Yip , Zhao Yang , Jinjie Ni , Chong Zhang , Yukun Ma , Chongjia Ni , Eng Siong Chng , Bin Ma

The task of video-to-speech aims to translate silent video of lip movement to its corresponding audio signal. Previous approaches to this task are generally limited to the case of a single speaker, but a method that accounts for multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-21 Dan Oneata , Adriana Stan , Horia Cucu

In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low…

Sound · Computer Science 2022-01-21 J. Yang , Lei He

Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important…

Sound · Computer Science 2025-07-08 Mathilde Abrassart , Nicolas Obin , Axel Roebel

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information.…

Sound · Computer Science 2024-09-11 Zhengyang Chen , Shuai Wang , Mingyang Zhang , Xuechen Liu , Junichi Yamagishi , Yanmin Qian

Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Ruijie Tao , Zhan Shi , Yidi Jiang , Tianchi Liu , Haizhou Li

Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training…

Sound · Computer Science 2019-04-10 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka , Nobukatsu Hojo

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

Computation and Language · Computer Science 2025-12-30 Jeongsoo Choi , Jaehun Kim , Joon Son Chung

Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that…

Machine Learning · Computer Science 2018-02-21 Eliya Nachmani , Adam Polyak , Yaniv Taigman , Lior Wolf

We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a linguistic decoder, an acoustic synthesizer, and a single attention module that…

Computation and Language · Computer Science 2022-05-19 Ye Jia , Michelle Tadmor Ramanovich , Tal Remez , Roi Pomerantz