English
Related papers

Related papers: Learning Disentangled Speech Representations

200 papers

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Machine Learning · Computer Science 2019-12-18 Fahimeh Bahmaninezhad , Shi-Xiong Zhang , Yong Xu , Meng Yu , John H. L. Hansen , Dong Yu

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both generate and understand audio. However, preserving key…

Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable…

Machine Learning · Computer Science 2020-10-24 Jiantao Wu , Lin Wang

We present a neural analysis and synthesis (NANSY) framework that can manipulate voice, pitch, and speed of an arbitrary speech signal. Most of the previous works have focused on using information bottleneck to disentangle analysis features…

Sound · Computer Science 2021-10-29 Hyeong-Seok Choi , Juheon Lee , Wansoo Kim , Jie Hwan Lee , Hoon Heo , Kyogu Lee

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…

Sound · Computer Science 2024-11-06 Julia Wilkins , Sivan Ding , Magdalena Fuentes , Juan Pablo Bello

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-23 Ruichu Cai , Zijian Li , Pengfei Wei , Jie Qiao , Kun Zhang , Zhifeng Hao

Speech data collected in real-world scenarios often encounters two issues. First, multiple sources may exist simultaneously, and the number of sources may vary with time. Second, the existence of background noise in recording is inevitable.…

Sound · Computer Science 2020-05-21 Yuan-Kuei Wu , Chao-I Tuan , Hung-yi Lee , Yu Tsao

Learning the disentangled representation of interpretable generative factors of data is one of the foundations to allow artificial intelligence to think like people. In this paper, we propose the analogical training strategy for the…

Machine Learning · Computer Science 2018-04-26 Zejian Li , Yongchuan Tang , Yongxing He

Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-18 Siyang Yuan , Pengyu Cheng , Ruiyi Zhang , Weituo Hao , Zhe Gan , Lawrence Carin

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…

Computation and Language · Computer Science 2021-01-26 Vikash Balasubramanian , Ivan Kobyzev , Hareesh Bahuleyan , Ilya Shapiro , Olga Vechtomova

In this study, Disentanglement in Difference(DiD) is proposed to address the inherent inconsistency between the statistical independence of latent variables and the goal of semantic disentanglement in disentanglement representation…

Machine Learning · Computer Science 2025-04-04 Xingshen Zhang , Lin Wang , Shuangrong Liu , Xintao Lu , Chaoran Pang , Bo Yang

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

Machine Learning · Computer Science 2016-02-09 William Whitney

Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents. Higgins et al.…

Machine Learning · Computer Science 2019-09-20 Hugo Caselles-Dupré , Michael Garcia-Ortiz , David Filliat

Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Zhuohang Dang , Minnan Luo , Chengyou Jia , Guang Dai , Jihong Wang , Xiaojun Chang , Jingdong Wang

Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent…

Computer Vision and Pattern Recognition · Computer Science 2019-10-24 Patrick Esser , Johannes Haux , Björn Ommer

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…

Computation and Language · Computer Science 2023-06-08 Shikhar Vashishth , Shikhar Bharadwaj , Sriram Ganapathy , Ankur Bapna , Min Ma , Wei Han , Vera Axelrod , Partha Talukdar

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-05 Tao Tu , Yuan-Jui Chen , Alexander H. Liu , Hung-yi Lee

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Danwei Cai , Weiqing Wang , Ming Li