English
Related papers

Related papers: Hierarchical disentangled representation learning …

200 papers

Voice conversion (VC) using sequence-to-sequence learning of context posterior probabilities is proposed. Conventional VC using shared context posterior probabilities predicts target speech parameters from the context posterior…

Sound · Computer Science 2017-08-08 Hiroyuki Miyoshi , Yuki Saito , Shinnosuke Takamichi , Hiroshi Saruwatari

Singing voice conversion is to convert a singer's voice to another one's voice without changing singing content. Recent work shows that unsupervised singing voice conversion can be achieved with an autoencoder-based approach [1]. However,…

Sound · Computer Science 2020-02-19 Chengqi Deng , Chengzhu Yu , Heng Lu , Chao Weng , Dong Yu

This paper addresses the extraction of the bird vocalization embedding from the whole song level using disentangled representation learning (DRL). Bird vocalization embeddings are necessary for large-scale bioacoustic tasks, and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-31 Runwu Shi , Katsutoshi Itoyama , Kazuhiro Nakadai

Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Matthew Baas , Herman Kamper

The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-09 Benjamin van Niekerk , Marc-André Carbonneau , Julian Zaïdi , Mathew Baas , Hugo Seuté , Herman Kamper

Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…

Sound · Computer Science 2025-10-13 Huu Tuong Tu , Huan Vu , cuong tien nguyen , Dien Hy Ngo , Nguyen Thi Thu Trang

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-10 Wen-Chin Huang , Tomoki Hayashi , Yi-Chiao Wu , Hirokazu Kameoka , Tomoki Toda

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity…

Sound · Computer Science 2023-09-27 Leyuan Qu , Taihao Li , Cornelius Weber , Theresa Pekarek-Rosin , Fuji Ren , Stefan Wermter

Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the…

Machine Learning · Computer Science 2019-08-23 Ju-chieh Chou , Cheng-chieh Yeh , Hung-yi Lee

We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that…

Sound · Computer Science 2021-04-29 Luyu Wang , Pauline Luc , Adria Recasens , Jean-Baptiste Alayrac , Aaron van den Oord

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Sound · Computer Science 2022-02-14 Trung Dang , Dung Tran , Peter Chin , Kazuhito Koishida

Speech-based depression detection (SDD) has emerged as a non-invasive and scalable alternative to conventional clinical assessments. However, existing methods still struggle to capture robust depression-related speech characteristics, which…

Computation and Language · Computer Science 2026-01-22 Yuxin Li , Eng Siong Chng , Cuntai Guan

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-02 Qingming Tang

We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Mohammad Adiban , Kalin Stefanov , Sabato Marco Siniscalchi , Giampiero Salvi

Singing voice conversion (SVC) aims to render the target singer's timbre while preserving melody and lyrics. However, existing zero-shot SVC systems remain fragile in real songs due to harmony interference, F0 errors, and the lack of…

In this work, we present an arbitrary-scale super-resolution (SR) method to enhance the resolution of scientific data, which often involves complex challenges such as continuity, multi-scale physics, and the intricacies of high-frequency…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Xihaier Luo , Xiaoning Qian , Byung-Jun Yoon

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-05 Arsha Nagrani , Joon Son Chung , Samuel Albanie , Andrew Zisserman

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Xinqi Zhu , Chang Xu , Dacheng Tao

We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives:…

Automatic singing voice understanding tasks, such as singer identification, singing voice transcription, and singing technique classification, benefit from data-driven approaches that utilize deep learning techniques. These approaches work…

Sound · Computer Science 2023-09-06 Yuya Yamamoto