English
Related papers

Related papers: Improving Speaker Representations Using Contrastiv…

200 papers

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-19 Chunyu Qiang , Hao Li , Yixin Tian , Ruibo Fu , Tao Wang , Longbiao Wang , Jianwu Dang

Anti-spoofing is the task of speech authentication. That is, identifying genuine human speech compared to spoofed speech. The main focus of this paper is to suggest new representations for genuine and spoofed speech, based on the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-28 Matan Karo , Arie Yeredor , Itshak Lapidot

Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-31 Tae Jin Park , Nithin Rao Koluguri , Jagadeesh Balam , Boris Ginsburg

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

Sound · Computer Science 2020-11-02 Jaesung Huh , Hee Soo Heo , Jingu Kang , Shinji Watanabe , Joon Son Chung

In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-29 Soonshin Seo , Ji-Hwan Kim

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Jiangmeng Li , Wenwen Qiang , Changwen Zheng , Bing Su , Hui Xiong

Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single…

Machine Learning · Computer Science 2022-11-28 Sangmin Bae , Sungnyun Kim , Jongwoo Ko , Gihun Lee , Seungjong Noh , Se-Young Yun

Automatic speaker verification (ASV) systems use a playback detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and played-back speech,…

Sound · Computer Science 2018-09-14 Fuming Fang , Junichi Yamagishi , Isao Echizen , Md Sahidullah , Tomi Kinnunen

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

Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, yielding significant…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-19 Themos Stafylakis , Anna Silnova , Johan Rohdin , Oldrich Plchot , Lukas Burget

This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Jenthe Thienpondt , Brecht Desplanques , Kris Demuynck

Despite the maturity of modern speaker verification technology, its performance still significantly degrades when facing non-neutrally-phonated (e.g., shouted and whispered) speech. To address this issue, in this paper, we propose a new…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-06 Iván López-Espejo , Santi Prieto , Alfonso Ortega , Eduardo Lleida

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…

Sound · Computer Science 2024-08-27 Zhenyu Wang , John H. L. Hansen

In this work, a novel solution to the speaker identification problem is proposed through minimization of statistical divergences between the probability distribution (g). of feature vectors from the test utterance and the probability…

Machine Learning · Statistics 2015-12-17 Ayanendranath Basu , Smarajit Bose , Amita Pal , Anish Mukherjee , Debasmita Das

Given one reference facial image and a piece of speech as input, talking head generation aims to synthesize a realistic-looking talking head video. However, generating a lip-synchronized video with natural head movements is challenging. The…

Multimedia · Computer Science 2023-02-28 Jianrong Wang , Yaxin Zhao , Li Liu , Hongkai Fan , Tianyi Xu , Qi Li , Sen Li

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-26 Youzhi Tu , Man-Wai Mak , Jen-Tzung Chien

Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events…

Sound · Computer Science 2024-01-12 Yadong Guan , Jiqing Han , Hongwei Song , Wenjie Song , Guibin Zheng , Tieran Zheng , Yongjun He

Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipelines; however, the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-30 Jaskirat Sudan , Hashim Ali , Surya Subramani , Hafiz Malik

Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due…

Computation and Language · Computer Science 2025-06-30 Hengyuan Zhang , Chenming Shang , Sizhe Wang , Dongdong Zhang , Yiyao Yu , Feng Yao , Renliang Sun , Yujiu Yang , Furu Wei

The front-end factor analysis (FEFA), an extension of principal component analysis (PPCA) tailored to be used with Gaussian mixture models (GMMs), is currently the prevalent approach to extract compact utterance-level features (i-vectors)…

Audio and Speech Processing · Electrical Eng. & Systems 2018-05-04 Ville Vestman , Tomi Kinnunen