English
Related papers

Related papers: Can you Remove the Downstream Model for Speaker Re…

200 papers

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

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…

Computation and Language · Computer Science 2024-06-24 Varsha Suresh , Salah Aït-Mokhtar , Caroline Brun , Ioan Calapodescu

Self-supervised models have had great success in learning speech representations that can generalize to various downstream tasks. However, most self-supervised models require a large amount of compute and multiple GPUs to train,…

Computation and Language · Computer Science 2024-09-02 Tzu-Quan Lin , Hung-yi Lee , Hao Tang

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-11 Junyi Peng , Lin Zhang , Jiangyu Han , Oldřich Plchot , Johan Rohdin , Themos Stafylakis , Shuai Wang , Jan Černocký

In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream…

Sound · Computer Science 2025-06-03 Ryan Whetten , Lucas Maison , Titouan Parcollet , Marco Dinarelli , Yannick Estève

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

Sound · Computer Science 2026-05-08 Magdalena Gołębiowska , Piotr Syga

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

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Multimedia · Computer Science 2022-12-07 Shinta Otake , Rei Kawakami , Nakamasa Inoue

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Sound · Computer Science 2022-02-14 Trung Dang , Dung Tran , Peter Chin , Kazuhito Koishida

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

Computation and Language · Computer Science 2024-06-13 Luis Lugo , Valentin Vielzeuf

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-05 Shuai Wang , Zhengyang Chen , Kong Aik Lee , Yanmin Qian , Haizhou Li

Speaker Verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-06 Kerlos Atia Abdalmalak , Ascensión Gallardo-Antol'in

Speaker recognition is a task of identifying persons from their voices. Recently, deep learning has dramatically revolutionized speaker recognition. However, there is lack of comprehensive reviews on the exciting progress. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Zhongxin Bai , Xiao-Lei Zhang

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…

Automatic speaker recognition algorithms typically use pre-defined filterbanks, such as Mel-Frequency and Gammatone filterbanks, for characterizing speech audio. However, it has been observed that the features extracted using these…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-14 Anurag Chowdhury , Arun Ross

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-17 Chengyi Wang , Yu Wu , Sanyuan Chen , Shujie Liu , Jinyu Li , Yao Qian , Zhenglu Yang

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

Speaker identification, determining which character said each utterance in literary text, benefits many downstream tasks. Most existing approaches use expert-defined rules or rule-based features to directly approach this task, but these…

Computation and Language · Computer Science 2022-10-13 Ben Zhou , Dian Yu , Dong Yu , Dan Roth

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-17 Shota Horiguchi , Takanori Ashihara , Marc Delcroix , Atsushi Ando , Naohiro Tawara

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Computation and Language · Computer Science 2022-04-20 Dan Berrebbi , Jiatong Shi , Brian Yan , Osbel Lopez-Francisco , Jonathan D. Amith , Shinji Watanabe