English
Related papers

Related papers: Self-Distillation Prototypes Network: Learning Rob…

200 papers

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Self-supervised speech representation learning enables the extraction of meaningful features from raw waveforms. These features can then be efficiently used across multiple downstream tasks. However, two significant issues arise when…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-14 Heitor R. Guimarães , Arthur Pimentel , Anderson R. Avila , Mehdi Rezagholizadeh , Boxing Chen , Tiago H. Falk

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 Themos Stafylakis , Johan Rohdin , Oldrich Plchot , Petr Mizera , Lukas Burget

With the continuous development of speech recognition technology, speaker verification (SV) has become an important method for identity authentication. Traditional SV methods rely on handcrafted feature extraction, while deep learning has…

Sound · Computer Science 2025-09-05 Zhaorui Sun , Yihao Chen , Jialong Wang , Minqiang Xu , Lei Fang , Sian Fang , Lin Liu

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

Sound · Computer Science 2018-12-27 Victoria Mingote , Antonio Miguel , Alfonso Ortega , Eduardo Lleida

Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Hongyu Wang , Hui Li , Bo Li

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

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

This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build…

The goal of this paper is to train effective self-supervised speaker representations without identity labels. We propose two curriculum learning strategies within a self-supervised learning framework. The first strategy aims to gradually…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Hee-Soo Heo , Jee-weon Jung , Jingu Kang , Youngki Kwon , You Jin Kim , Bong-Jin Lee , Joon Son Chung

Background noise considerably reduces the accuracy and reliability of speaker verification (SV) systems. These challenges can be addressed using a speech enhancement system as a front-end module. Recently, diffusion probabilistic models…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-20 Ju-ho Kim , Jungwoo Heo , Hyun-seo Shin , Chan-yeong Lim , Ha-Jin Yu

Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to the target representations. In…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Xingbin Liu , Jinghao Zhou , Tao Kong , Xianming Lin , Rongrong Ji

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-05 Raghuveer Peri , Monisankha Pal , Arindam Jati , Krishna Somandepalli , Shrikanth Narayanan

The promising performance of Deep Learning (DL) in speech recognition has motivated the use of DL in other speech technology applications such as speaker recognition. Given i-vectors as inputs, the authors proposed an impostor selection…

Sound · Computer Science 2017-04-24 Omid Ghahabi , Javier Hernando

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On…

Sound · Computer Science 2022-12-07 Zhiyuan Peng , Xuanji He , Ke Ding , Tan Lee , Guanglu Wan

Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 Yunqi Cai , Lantian Li , Dong Wang , Andrew Abel

Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-supervised learning methods consists in the effective use of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Yanyan Wang , Kechen Song , Yuyuan Liu , Shuai Ma , Yunhui Yan , Gustavo Carneiro

This paper proposes a novel Sequence-to-Sequence Neural Diarization (S2SND) framework to perform online and offline speaker diarization. It is developed from the sequence-to-sequence architecture of our previous target-speaker voice…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-24 Ming Cheng , Yuke Lin , Ming Li

The quantization of deep neural networks (QDNNs) has been actively studied for deployment in edge devices. Recent studies employ the knowledge distillation (KD) method to improve the performance of quantized networks. In this study, we…

Machine Learning · Computer Science 2020-10-01 Yoonho Boo , Sungho Shin , Jungwook Choi , Wonyong Sung

This paper presents a novel design of attention model for text-independent speaker verification. The model takes a pair of input utterances and generates an utterance-level embedding to represent speaker-specific characteristics in each…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-14 Jingyu Li , Tan Lee