English
Related papers

Related papers: Exploring Disentanglement with Multilingual and Mo…

200 papers

Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the…

Sound · Computer Science 2024-09-05 Yan Rong , Li Liu

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

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize…

Sound · Computer Science 2025-09-11 Youngjun Sim , Jinsung Yoon , Wooyeol Jeong , Young-Joo Suh

In Emotion Recognition in Conversations (ERC), the emotions of target utterances are closely dependent on their context. Therefore, existing works train the model to generate the response of the target utterance, which aims to recognise…

Computation and Language · Computer Science 2023-05-30 Kailai Yang , Tianlin Zhang , Sophia Ananiadou

Cross-domain disentanglement is the problem of learning representations partitioned into domain-invariant and domain-specific representations, which is a key to successful domain transfer or measuring semantic distance between two domains.…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 HyeongJoo Hwang , Geon-Hyeong Kim , Seunghoon Hong , Kee-Eung Kim

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

Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair…

Machine Learning · Computer Science 2020-07-09 Sungho Park , Dohyung Kim , Sunhee Hwang , Hyeran Byun

In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-27 Nishant Gurunath , Sai Krishna Rallabandi , Alan Black

Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research…

Machine Learning · Computer Science 2025-07-18 Ankur Garg , Xuemin Yu , Hassan Sajjad , Samira Ebrahimi Kahou

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

Machine Learning · Computer Science 2023-02-06 John Harvill , Jarred Barber , Arun Nair , Ramin Pishehvar

The goal of voice anonymization is to modify an audio such that the true identity of its speaker is hidden. Research on this task is typically limited to the same English read speech datasets, thus the efficacy of current methods for other…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-03 Sarina Meyer , Ekaterina Kolos , Ngoc Thang Vu

One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and…

Sound · Computer Science 2024-11-26 Pengcheng Li , Jianzong Wang , Xulong Zhang , Yong Zhang , Jing Xiao , Ning Cheng

Most recent speech privacy efforts have focused on anonymizing acoustic speaker attributes but there has not been as much research into protecting information from speech content. We introduce a toy problem that explores an emerging type of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Jennifer Williams , Karla Pizzi , Paul-Gauthier Noe , Sneha Das

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

Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify.…

Computation and Language · Computer Science 2022-04-04 Jake Vasilakes , Chrysoula Zerva , Makoto Miwa , Sophia Ananiadou

Voice Conversion (VC) converts the voice of a source speech to that of a target while maintaining the source's content. Speech can be mainly decomposed into four components: content, timbre, rhythm and pitch. Unfortunately, most related…

Sound · Computer Science 2023-06-22 Zhonghua Liu , Shijun Wang , Ning Chen

All previous methods for audio-driven talking head generation assume the input audio to be clean with a neutral tone. As we show empirically, one can easily break these systems by simply adding certain background noise to the utterance or…

Computer Vision and Pattern Recognition · Computer Science 2019-10-03 Gaurav Mittal , Baoyuan Wang

Leveraging the fact that speaker identity and content vary on different time scales, \acrlong{fhvae} (\acrshort{fhvae}) uses different latent variables to symbolize these two attributes. Disentanglement of these attributes is carried out by…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-16 Yuying Xie , Thomas Arildsen , Zheng-Hua Tan

In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…

Machine Learning · Computer Science 2023-10-24 Kyle Hsu , Will Dorrell , James C. R. Whittington , Jiajun Wu , Chelsea Finn