English
Related papers

Related papers: Disentangled Speech Representation Learning for On…

200 papers

The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "disentanglement", where a representation contains only parts of…

Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning. In this work, we focus on semi-supervised disentanglement learning and extend work by Locatello et al. (2019) by…

Machine Learning · Computer Science 2020-06-24 Weili Nie , Zichao Wang , Ankit B. Patel , Richard G. Baraniuk

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned…

The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and…

Sound · Computer Science 2025-01-15 Jaehun Kim , Ji-Hoon Kim , Yeunju Choi , Tan Dat Nguyen , Seongkyu Mun , Joon Son Chung

The goal of a classification model is to assign the correct labels to data. In most cases, this data is not fully described by the given set of labels. Often a rich set of meaningful concepts exist in the domain that can much more precisely…

Machine Learning · Computer Science 2021-08-23 Yoeri Poels , Vlado Menkovski

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-28 Pu Wang , Hugo Van hamme

Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides…

Machine Learning · Statistics 2018-05-30 Wei-Ning Hsu , James Glass

Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a…

Sound · Computer Science 2022-08-23 Ziang Long , Yunling Zheng , Meng Yu , Jack Xin

We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting. Our goal is to map an input image to an identity-invariant latent representation that captures…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Chao Yang , Xiaofeng Liu , Qingming Tang , C. -C. Jay Kuo

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Sound · Computer Science 2025-06-04 Aditya Srinivas Menon , Raj Prakash Gohil , Kumud Tripathi , Pankaj Wasnik

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…

Machine Learning · Statistics 2019-09-12 Jan Stühmer , Richard E. Turner , Sebastian Nowozin

This study tackles unsupervised subword modeling in the zero-resource scenario, learning frame-level speech representation that is phonetically discriminative and speaker-invariant, using only untranscribed speech for target languages.…

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

We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the…

Machine Learning · Statistics 2019-06-13 Emile Mathieu , Tom Rainforth , N. Siddharth , Yee Whye Teh

The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre…

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance…

Computation and Language · Computer Science 2021-06-22 Andros Tjandra , Ruoming Pang , Yu Zhang , Shigeki Karita

In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable models have been shown to learn nontrivial…

Finding disentangled representation plays a predominant role in the success of modern deep learning applications, but the results lack a straightforward explanation. Here we apply the information bottleneck method and its $\beta$-VAE…

Strongly Correlated Electrons · Physics 2022-07-01 Dongchen Huang , Danqing Hu , Yi-feng Yang

One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during training, tend to lose…

Machine Learning · Computer Science 2023-10-05 Jiantao Wu , Shentong Mo , Xiang Yang , Muhammad Awais , Sara Atito , Xingshen Zhang , Lin Wang , Xiang Yang

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-06 Jie Wang , Jingbei Li , Xintao Zhao , Zhiyong Wu , Shiyin Kang , Helen Meng

Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech…

Sound · Computer Science 2022-02-23 Qiqi Wang , Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao
‹ Prev 1 3 4 5 6 7 10 Next ›