English
Related papers

Related papers: Learning Decoupling Features Through Orthogonality…

200 papers

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…

Sound · Computer Science 2025-05-27 Giuseppe Ruggiero , Matteo Testa , Jurgen Van de Walle , Luigi Di Caro

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

Machine Learning · Computer Science 2025-06-03 Jiali Cheng , Hadi Amiri

In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt a close-talk well-trained production AM to far-field by…

Computation and Language · Computer Science 2018-04-17 Jinyu Li , Rui Zhao , Zhuo Chen , Changliang Liu , Xiong Xiao , Guoli Ye , Yifan Gong

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

Sound · Computer Science 2023-02-28 Xue Jiang , Xiulian Peng , Yuan Zhang , Yan Lu

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Computation and Language · Computer Science 2020-05-25 Yanpei Shi , Qiang Huang , Thomas Hain

This paper proposes an improved approach for open-set speaker identification based on pretrained speaker foundation models. Building upon the previous Speaker Reciprocal Points Learning framework (V1), we first introduce an enhanced…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-16 Zhiyong Chen , Shuhang Wu , Yingjie Duan , Xinkang Xu , Xinhui Hu

In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-24 Rongjin Li , Weibin Zhang , Dongpeng Chen , Jintao Kang , Xiaofen Xing

Keyword spotting (KWS) provides a critical user interface for many mobile and edge applications, including phones, wearables, and cars. As KWS systems are typically 'always on', maximizing both accuracy and power efficiency are central to…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-11 Peter Blouw , Gurshaant Malik , Benjamin Morcos , Aaron R. Voelker , Chris Eliasmith

Voice activity and overlapped speech detection (respectively VAD and OSD) are key pre-processing tasks for speaker diarization. The final segmentation performance highly relies on the robustness of these sub-tasks. Recent studies have shown…

In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verification performance. We implement an idea of speaker-utterance…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-21 Tianchi Liu , Rohan Kumar Das , Maulik Madhavi , Shengmei Shen , Haizhou Li

Semantic segmentation and stereo matching, respectively analogous to the ventral and dorsal streams in our human brain, are two key components of autonomous driving perception systems. Addressing these two tasks with separate networks is no…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Guanfeng Tang , Zhiyuan Wu , Jiahang Li , Ping Zhong , We Ye , Xieyuanli Chen , Huiming Lu , Rui Fan

In service robotics, there is an interest to identify the user by voice alone. However, in application scenarios where a service robot acts as a waiter or a store clerk, new users are expected to enter the environment frequently. Typically,…

Audio and Speech Processing · Electrical Eng. & Systems 2018-09-13 Ivette Vélez , Caleb Rascon , Gibrán Fuentes-Pineda

Voice-based interfaces rely on a wake-up word mechanism to initiate communication with devices. However, achieving a robust, energy-efficient, and fast detection remains a challenge. This paper addresses these real production needs by…

Sound · Computer Science 2023-10-18 Fernando López , Jordi Luque , Carlos Segura , Pablo Gómez

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability. Speaking rate mismatch is often observed in practical speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-31 Fuchuan Tong , Siqi Zheng , Haodong Zhou , Xingjia Xie , Qingyang Hong , Lin Li

Keyword spotting and in particular Wake-Up-Word (WUW) detection is a very important task for voice assistants. A very common issue of voice assistants is that they get easily activated by background noise like music, TV or background speech…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-01 David Bonet , Guillermo Cámbara , Fernando López , Pablo Gómez , Carlos Segura , Jordi Luque

In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such representations are still vulnerable to emotion variability. To…

Sound · Computer Science 2025-05-27 Jingguang Tian , Xinhui Hu , Xinkang Xu

Self-supervised speech representations can hugely benefit downstream speech technologies, yet the properties that make them useful are still poorly understood. Two candidate properties related to the geometry of the representation space…

Computation and Language · Computer Science 2024-06-14 Mukhtar Mohamed , Oli Danyi Liu , Hao Tang , Sharon Goldwater

Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To…

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

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Yanpei Shi , Qiang Huang , Thomas Hain