English
Related papers

Related papers: Self-Supervised Speech Representations Preserve Sp…

200 papers

In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content,…

Sound · Computer Science 2023-02-17 Shehzeen Hussain , Paarth Neekhara , Jocelyn Huang , Jason Li , Boris Ginsburg

The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary evaluation of the challenge submissions was done through…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-09 Rohan Kumar Das , Tomi Kinnunen , Wen-Chin Huang , Zhenhua Ling , Junichi Yamagishi , Yi Zhao , Xiaohai Tian , Tomoki Toda

The success of deep learning in speaker recognition relies heavily on the use of large datasets. However, the data-hungry nature of deep learning methods has already being questioned on account the ethical, privacy, and legal concerns that…

Enhancing speech quality is an indispensable yet difficult task as it is often complicated by a range of degradation factors. In addition to additive noise, reverberation, clipping, and speech attenuation can all adversely affect speech…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-01 Jaeuk Byun , Youna Ji , Soo Whan Chung , Soyeon Choe , Min Seok Choi

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

Computation and Language · Computer Science 2017-09-25 Wei-Ning Hsu , Yu Zhang , James Glass

In our previous work, we proposed a language-independent speaker anonymization system based on self-supervised learning models. Although the system can anonymize speech data of any language, the anonymization was imperfect, and the speech…

Sound · Computer Science 2022-03-29 Xiaoxiao Miao , Xin Wang , Erica Cooper , Junichi Yamagishi , Natalia Tomashenko

There has been a growing demand for automated spoken language assessment systems in recent years. A standard pipeline for this process is to start with a speech recognition system and derive features, either hand-crafted or based on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-17 Stefano Bannò , Kate M. Knill , Marco Matassoni , Vyas Raina , Mark J. F. Gales

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-09 Da-Yi Wu , Yen-Hao Chen , Hung-Yi Lee

Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Jiachen Lian , Chunlei Zhang , Dong Yu

We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the…

Computation and Language · Computer Science 2020-05-20 Alexei Baevski , Michael Auli , Abdelrahman Mohamed

This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…

Sound · Computer Science 2025-07-09 Nik Vaessen , Roeland Ordelman , David A. van Leeuwen

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-19 Yuchen Hu , Chen Chen , Qiushi Zhu , Eng Siong Chng

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label…

Sound · Computer Science 2024-02-27 Szu-Wei Fu , Kuo-Hsuan Hung , Yu Tsao , Yu-Chiang Frank Wang

Speech anonymisation aims to protect speaker identity by changing personal identifiers in speech while retaining linguistic content. Current methods fail to retain prosody and unique speech patterns found in elderly and pathological speech…

Artificial Intelligence · Computer Science 2024-10-22 Suhita Ghosh , Melanie Jouaiti , Arnab Das , Yamini Sinha , Tim Polzehl , Ingo Siegert , Sebastian Stober

Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-22 Shehzeen Hussain , Van Nguyen , Shuhua Zhang , Erik Visser

Automatic speech recognition (ASR) systems become increasingly efficient thanks to new advances in neural network training like self-supervised learning. However, they are known to be unfair toward certain groups, for instance, people…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-07 Lucas Maison , Yannick Estève

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a…

Sound · Computer Science 2025-08-19 Beilong Tang , Xiaoxiao Miao , Xin Wang , Ming Li

Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to…

Sound · Computer Science 2024-06-25 Yassine El Kheir , Ahmed Ali , Shammur Absar Chowdhury