English
Related papers

Related papers: Angular Softmax Loss for End-to-end Speaker Verifi…

200 papers

The challenge of fairness arises when Automatic Speech Recognition (ASR) systems do not perform equally well for all sub-groups of the population. In the past few years there have been many improvements in overall speech recognition…

Sound · Computer Science 2023-06-12 Irina-Elena Veliche , Pascale Fung

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

Computation and Language · Computer Science 2020-02-17 Marco Dinarelli , Nikita Kapoor , Bassam Jabaian , Laurent Besacier

Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-11 Hervé Bredin , Antoine Laurent

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-12 Zehai Tu , Jack Deadman , Ning Ma , Jon Barker

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple…

Computer Vision and Pattern Recognition · Computer Science 2018-12-03 Binghui Chen , Weihong Deng , Haifeng Shen

In Sound Event Detection (SED) systems, the lengths of median filters for post-processing have never been optimized during training due to several problems. No gradient is received by the lengths so they cannot be learned during…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-23 Fengnian Zhao , Ruwei Li , Xin Liu , Liwen Xu

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Qiujia Li , David Qiu , Yu Zhang , Bo Li , Yanzhang He , Philip C. Woodland , Liangliang Cao , Trevor Strohman

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

Machine Learning · Statistics 2019-09-19 Ugo Tanielian , Flavian Vasile

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Ye-Rin Jeoung , Joon-Young Yang , Jeong-Hwan Choi , Joon-Hyuk Chang

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh

Despite successful applications of end-to-end approaches in multi-channel speech recognition, the performance still degrades severely when the speech is corrupted by reverberation. In this paper, we integrate the dereverberation module into…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-18 Wangyou Zhang , Aswin Shanmugam Subramanian , Xuankai Chang , Shinji Watanabe , Yanmin Qian

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Computation and Language · Computer Science 2019-02-20 Shruti Palaskar , Vikas Raunak , Florian Metze

Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory requirements hinder…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-03 Bei Liu , Yanmin Qian

This paper presents a linear regression based back-end for speaker verification. Linear regression is a simple linear model that minimizes the mean squared estimation error between the target and its estimate with a closed form solution,…

Sound · Computer Science 2018-02-13 Xiao-Lei Zhang

End-to-end neural diarization (EEND) models offer significant improvements over traditional embedding-based Speaker Diarization (SD) approaches but falls short on generalizing to long-form audio with large number of speakers.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-28 Xiang Li , Vivek Govindan , Rohit Paturi , Sundararajan Srinivasan

Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-03 Ashutosh Chaubey , Sparsh Sinha , Susmita Ghose

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-19 Vishwas M. Shetty , Metilda Sagaya Mary N J , S. Umesh

In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR). First, we study an approach where uni-modal deep networks are trained separately…

Computation and Language · Computer Science 2015-01-23 Youssef Mroueh , Etienne Marcheret , Vaibhava Goel

A typical pipeline for Zero-Shot Learning (ZSL) is to integrate the visual features and the class semantic descriptors into a multimodal framework with a linear or bilinear model. However, the visual features and the class semantic…

Computer Vision and Pattern Recognition · Computer Science 2017-05-23 Zhong Ji , Yunxin Sun , Yulong Yu , Jichang Guo , Yanwei Pang

In this paper, Whisper, a large-scale pre-trained model for automatic speech recognition, is proposed to apply to speaker verification. A partial multi-scale feature aggregation (PMFA) approach is proposed based on a subset of Whisper…

Sound · Computer Science 2024-08-29 Yiyang Zhao , Shuai Wang , Guangzhi Sun , Zehua Chen , Chao Zhang , Mingxing Xu , Thomas Fang Zheng