English
Related papers

Related papers: Learning Hidden Unit Contributions for Unsupervise…

200 papers

Most speech enhancement (SE) models learn a point estimate and do not make use of uncertainty estimation in the learning process. In this paper, we show that modeling heteroscedastic uncertainty by minimizing a multivariate Gaussian…

Sound · Computer Science 2023-03-09 Kuan-Lin Chen , Daniel D. E. Wong , Ke Tan , Buye Xu , Anurag Kumar , Vamsi Krishna Ithapu

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

Computation and Language · Computer Science 2021-06-04 Richard Diehl Martinez , Scott Novotney , Ivan Bulyko , Ariya Rastrow , Andreas Stolcke , Ankur Gandhe

Acoustic echo cancellation (AEC) is designed to remove echoes, reverberation, and unwanted added sounds from the microphone signal while maintaining the quality of the near-end speaker's speech. This paper proposes adaptive speech quality…

Sound · Computer Science 2022-11-10 Bozhong Liu , Xiaoxi Yu , Hantao Huang

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Songsong Wu , Yan Yan , Hao Tang , Jianjun Qian , Jian Zhang , Xiao-Yuan Jing

In this paper we propose a method to model speaker and session variability and able to generate likelihood ratios using neural networks in an end-to-end phrase dependent speaker verification system. As in Joint Factor Analysis, the model…

Audio and Speech Processing · Electrical Eng. & Systems 2019-01-01 Antonio Miguel , Jorge Llombart , Alfonso Ortega , Eduardo Lleida

Modern speaker verification models use deep neural networks to encode utterance audio into discriminative embedding vectors. During the training process, these networks are typically optimized to differentiate arbitrary speakers. This…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-09 Hua Shen , Yuguang Yang , Guoli Sun , Ryan Langman , Eunjung Han , Jasha Droppo , Andreas Stolcke

Self-supervised learning (SSL) speech models, which can serve as powerful upstream models to extract meaningful speech representations, have achieved unprecedented success in speech representation learning. However, their effectiveness on…

Sound · Computer Science 2023-02-01 Tung-Yu Wu , Chen-An Li , Tzu-Han Lin , Tsu-Yuan Hsu , Hung-Yi Lee

Speech systems developed for a particular choice of acoustic domain and sampling frequency do not translate easily to others. The usual practice is to learn domain adaptation and bandwidth extension models independently. Contrary to this,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Saurabh Kataria , Jesús Villalba , Laureano Moro-Velázquez , Najim Dehak

In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Seong Min Kye , Youngmoon Jung , Hae Beom Lee , Sung Ju Hwang , Hoirin Kim

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

Sound · Computer Science 2024-04-30 Wenbin Wang , Yang Song , Sanjay Jha

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Xiaofeng Ge , Jiangyu Han , Haixin Guan , Yanhua Long

Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…

Semi-supervised learning and domain adaptation techniques have drawn increasing attention in the field of domestic sound event detection thanks to the availability of large amounts of unlabeled data and the relative ease to generate…

Sound · Computer Science 2022-08-18 Fang-Ching Chen , Kuan-Dar Chen , Yi-Wen Liu

Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated the usage of neural speaker embeddings for an ASR system. In…

Computation and Language · Computer Science 2023-09-21 Christoph Lüscher , Jingjing Xu , Mohammad Zeineldeen , Ralf Schlüter , Hermann Ney

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…

Computation and Language · Computer Science 2021-04-14 Di Wu , Yiren Chen , Liang Ding , Dacheng Tao

Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environments despite the inclusion of noise suppression feature.…

Sound · Computer Science 2021-06-10 Zehai Tu , Ning Ma , Jon Barker

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Sound · Computer Science 2024-08-27 Zhaoxi Mu , Xinyu Yang , Sining Sun , Qing Yang

Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Saurabh Kataria , Jesús Villalba , Najim Dehak

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

Sound · Computer Science 2020-11-24 Xiaoyi Qin , Yaogen Yang , Lin Yang , Xuyang Wang , Junjie Wang , Ming Li
‹ Prev 1 8 9 10 Next ›