English
Related papers

Related papers: Learning De-identified Representations of Prosody …

200 papers

We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw…

Computation and Language · Computer Science 2024-12-05 Joonyong Park , Daisuke Saito , Nobuaki Minematsu

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

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

Sound · Computer Science 2024-01-19 Yimin Deng , Huaizhen Tang , Xulong Zhang , Ning Cheng , Jing Xiao , Jianzong Wang

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-13 Sung Hwan Mun , Min Hyun Han , Minchan Kim , Dongjune Lee , Nam Soo Kim

There has been a lot of prior work on representation learning for speech recognition applications, but not much emphasis has been given to an investigation of effective representations of affect from speech, where the paralinguistic…

Computation and Language · Computer Science 2016-02-16 Sayan Ghosh , Eugene Laksana , Louis-Philippe Morency , Stefan Scherer

Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach. Our main objective is to make our network learn…

Sound · Computer Science 2022-06-28 Sreyan Ghosh , Ashish Seth , and Deepak Mittal , Maneesh Singh , S. Umesh

Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-14 Eray Eren , Qingju Liu , Hyeongwoo Kim , Pablo Garrido , Abeer Alwan

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Computation and Language · Computer Science 2025-10-30 Shreyas Gopal , Ashutosh Anshul , Haoyang Li , Yue Heng Yeo , Hexin Liu , Eng Siong Chng

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

Sound · Computer Science 2024-06-21 KiHyun Nam , Hee-Soo Heo , Jee-weon Jung , Joon Son Chung

Identifying whether an utterance is a statement, question, greeting, and so forth is integral to effective automatic understanding of natural dialog. Little is known, however, about how such dialog acts (DAs) can be automatically classified…

Computation and Language · Computer Science 2007-05-23 E. Shriberg , R. Bates , A. Stolcke , P. Taylor , D. Jurafsky , K. Ries , N. Coccaro , R. Martin , M. Meteer , C. Van Ess-Dykema

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-25 Théo Lepage , Réda Dehak

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Computation and Language · Computer Science 2019-06-20 Yu-An Chung , Wei-Ning Hsu , Hao Tang , James Glass

This work proposes a method for source device identification from speech recordings that applies neural-network-based denoising, to mitigate the impact of counter-forensics attacks using noise injection. The method is evaluated by comparing…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-27 Antonio Giganti , Luca Cuccovillo , Paolo Bestagini , Patrick Aichroth , Stefano Tubaro

Human auditory perception is compositional in nature -- we identify auditory streams from auditory scenes with multiple sound events. However, such auditory scenes are typically represented using clip-level representations that do not…

Sound · Computer Science 2025-03-04 Sripathi Sridhar , Mark Cartwright

Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-22 Toranosuke Manabe , Yuchi Ishikawa , Hokuto Munakata , Tatsuya Komatsu

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

Machine Learning · Computer Science 2023-07-04 Hananeh Aliee , Ferdinand Kapl , Soroor Hediyeh-Zadeh , Fabian J. Theis

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…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each…

Sound · Computer Science 2020-10-26 Ruilin Xu , Rundi Wu , Yuko Ishiwaka , Carl Vondrick , Changxi Zheng

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