English
Related papers

Related papers: Disentangled Representation Learning for Environme…

200 papers

Human speech contains both linguistic content and speaker dependent characteristics making speaker verification a key technology in identity critical applications. Modern deep learning speaker verification systems aim to learn speaker…

Sound · Computer Science 2026-03-09 Nikos Chazaridis , Mohammad Belal , Rafael Mestre , Timothy J. Norman , Christine Evers

This paper proposes an interesting voice and accent joint conversion approach, which can convert an arbitrary source speaker's voice to a target speaker with non-native accent. This problem is challenging as each target speaker only has…

Sound · Computer Science 2020-11-18 Zhichao Wang , Wenshuo Ge , Xiong Wang , Shan Yang , Wendong Gan , Haitao Chen , Hai Li , Lei Xie , Xiulin Li

While neural-based models have led to significant advancements in audio feature extraction, the interpretability of the learned representations remains a critical challenge. To address this, disentanglement techniques have been integrated…

Sound · Computer Science 2025-10-07 Benoît Giniès , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand…

Audio and Speech Processing · Electrical Eng. & Systems 2018-09-13 Suwon Shon , Hao Tang , James Glass

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-08 Federico Costa , Miquel India , Javier Hernando

Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance…

Image and Video Processing · Electrical Eng. & Systems 2021-02-15 Raghuveer Peri , Srinivas Parthasarathy , Charles Bradshaw , Shiva Sundaram

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

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and…

Machine Learning · Computer Science 2020-07-09 Xavier Favory , Konstantinos Drossos , Tuomas Virtanen , Xavier Serra

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-19 Xu Xiang , Shuai Wang , Houjun Huang , Yanmin Qian , Kai Yu

Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Sanghyeok Chu , Dongwan Kim , Bohyung Han

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training.…

Sound · Computer Science 2021-06-22 Hongqiang Du , Lei Xie

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-07 Adriana Stan

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-18 Mingjie Chen , Thomas Hain

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

Machine Learning · Computer Science 2019-09-12 Jan Chorowski , Ron J. Weiss , Samy Bengio , Aäron van den Oord

Speaker diarization remains challenging due to the need for structured speaker representations, efficient modeling, and robustness to varying conditions. We propose a performant, compact diarization framework that integrates conformer…

Sound · Computer Science 2025-06-16 David Palzer , Matthew Maciejewski , Eric Fosler-Lussier

Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a…

Sound · Computer Science 2023-03-01 Dianwen Ng , Ruixi Zhang , Jia Qi Yip , Zhao Yang , Jinjie Ni , Chong Zhang , Yukun Ma , Chongjia Ni , Eng Siong Chng , Bin Ma

The ability to extract generative parameters from high-dimensional fields of data in an unsupervised manner is a highly desirable yet unrealized goal in computational physics. This work explores the use of variational autoencoders (VAEs)…

Computational Physics · Physics 2021-11-16 Christian Jacobsen , Karthik Duraisamy

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Siyuan Feng , Tan Lee , Zhiyuan Peng

We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker…

Sound · Computer Science 2019-06-25 Shuo Liu , Gil Keren , Björn Schuller

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

Computation and Language · Computer Science 2021-09-14 Xiongyi Zhang , Jan-Willem van de Meent , Byron C. Wallace
‹ Prev 1 3 4 5 6 7 10 Next ›