检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Wang, Shuai Huang, Zili Qian, Yanmin Yu, Kai Key Laboratory of Shanghai Education Commission for Intelligent Interaction Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

Linear Discriminant Analysis (LDA) has been used as a standard post-processing procedure in many state-of-the-art speaker recognition tasks. Through maximizing the inter-speaker difference and minimizing the intra-speaker variation, LDA projects i-vectors to a lower-dimensional and more discriminative subspace. In this paper, we propose a neural network based compensation scheme(termed as deep discriminant analysis, DDA) for i-vector based speaker recognition, which shares the spirit with LDA. Optimized against softmax loss and center loss at the same time, the proposed method learns a more compact and discriminative embedding space. Compared with the Gaussian distribution assumption of data and the learnt linear projection in LDA, the proposed method doesn't pose any assumptions on data and can learn a non-linear projection function. Experiments are carried out on a short-duration text-independent dataset based on the SRE Corpus, noticeable performance improvement can be observed against the normal LDA or PLDA methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

SEMI-SUPERVISED TRAINING USING ADVERSARIAL MULTI-TASK LEARNING FOR SPOKEN LANGUAGE UNDERSTANDING

SEMI-SUPERVISED TRAINING USING ADVERSARIAL MULTI-TASK LEARNI...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Ouyu Lan Su Zhu Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Spoken language understanding (SLU) usually requires human semantic annotation on collected data, but the process is expensive. In order to make better use of unlabeled data for robust SLU, we propose an adversarial multi-task learning method by merging a bidirectional language model (BLM) and a slot tagging model (STM). As a secondary objective, the BLM is used to learn generalized and unsupervised knowledge with abundant unlabeled data and improve the performance of STM on unseen data samples. We construct a shared space for both tasks and independent private spaces for each task respectively. Additional adversarial task discriminator is also used to obtain more task-independent sharing information. Experiments show that the proposed approaches achieve the state-of-the-art performance on the small scale ATIS benchmark and significantly improve the semi-supervised performance on a large-scale dataset.

关键词： Spoken language understanding Multitask learning Semi-supervised learning Adversarial task discriminator spoken language understanding Semi-supervised Learning STACK TRITIUM MONITOR Scanning Tunneling Microscope Data sampling BLM gene Data Collection Methods

来源：评论

学校读者我要写书评

暂无评论

Time-Frequency Masking Based Online Speech Enhancement with Multi-Channel Data Using Convolutional Neural Networks

Time-Frequency Masking Based Online Speech Enhancement with ...

引用

International Workshop on Acoustic Signal Enhancement (IWAENC)

作者： Soumitro Chakrabarty DeLiang Wang Emanuel A. P. Habets International Audio Laboratories Erlangen Germany Department of Computer Science and Engineering Center for Cognitive & Brain Sciences The Ohio State University USA

Speech enhancement in noisy and reverberant conditions remains a challenging task. In this work, a time-frequency masking based method for speech enhancement with multi -channel data using convolutional neural networks (CNN) is proposed, where the CNN is trained to estimate the ideal ratio mask by discriminating directional speech source from diffuse or spatially uncorrelated noise. The proposed method operates on, frame-by-frame, the magnitude and phase components of the short-time Fourier transform coefficients of all frequency sub-bands and microphones. The avoidance of temporal context and explicit feature extraction makes the proposed method suitable for online implementation. In contrast to most speech enhancement methods that utilize multi -channel data, the proposed method does not require information about the spatial position of the desired speech source. Through experimental evaluation with both simulated and real data, we show the robustness of the proposed method to unseen acoustic conditions as well as varying noise levels.

关键词： Microphones Speech enhancement Time-frequency analysis Acoustics Signal to noise ratio Task analysis Training data

来源：评论

学校读者我要写书评

暂无评论

Robust Spoken Language Understanding with Unsupervised ASR-Error Adaptation

Robust Spoken Language Understanding with Unsupervised ASR-E...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Su Zhu Ouyu Lan Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Robustness to errors produced by automatic speech recognition (ASR) is essential for Spoken Language Understanding (SLU). Traditional robust SLU typically needs ASR hypotheses with semantic annotations for training. However, semantic annotation is very expensive, and the corresponding ASR system may change frequently. Here, we propose a novel unsupervised ASR-error adaptation method, obviating the need of annotated ASR hypotheses. It only requires semantically annotated transcripts for the slot-tagging task and the transcripts paired with hypotheses for an input sentence reconstruction task. In this method, feature encoders which share part of the parameters are exploited to enforce the tasks in a similar feature space. Therefore, the transcript side slot-tagging model can be transferred to ASR hypotheses side easily. Experiments show that the proposed approach can yield significant improvement over strong baselines, and achieve performance very close to the oracle system.

关键词： Spoken Language understanding ASR-error robustness adversarial adaptation spoken language understanding Speech recognition aquifer storage and recovery spoken language Eigenvector transcript Religious Missions ANNOTATIONS

来源：评论

学校读者我要写书评

暂无评论

Joint I-Vector with End-to-End System for Short Duration Text-Independent Speaker Verification

Joint I-Vector with End-to-End System for Short Duration Tex...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zili Huang Shuai Wang Yanmin Qian Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781538646595

Factor analysis based i-vector has been the state-of-the-art method for speaker verification. Recently, researchers propose to build DNN based end-to-end speaker verification systems and achieve comparable performance with i -vector. Since these two methods possess their own property and differ from each other significantly, we explore a framework to integrate these two paradigms together to utilize their complementarity. More specifically, in this paper we develop and compare four methodologies to integrate traditional i -vector into end-to-end systems, including score fusion, embeddings concatenation, transformed concatenation and joint learning. All these approaches achieve significant gains. Moreover, the hard trial selection is performed on the end-to-end architecture which further improves the performance. Experimental results on a text-independent short-duration dataset generated from SRE 2010 reveal that the newly proposed method reduces the EER by relative 31.0% and 28.2% compared to the i-vector and end-to-end baselines respectively.

关键词： speaker verification end-to-end i-vector triplet loss hard trial selection speaker recognition end-to-end end system Loudspeakers Joints energy efficiency ratio Short circuits

来源：评论

学校读者我要写书评

暂无评论

Author Correction: A cross-cohort replicable and heritable latent dimension linking behaviour to multi-featured brain structure

Communications biology

引用

Communications biology 2023年第1期6卷 281页

作者： Eliana Nicolaisen-Sobesky Agoston Mihalik Shahrzad Kharabian-Masouleh Fabio S Ferreira Felix Hoffstaedter Holger Schwender Somayeh Maleki Balajoo Sofie L Valk Simon B Eickhoff B T Thomas Yeo Janaina Mourao-Miranda Sarah Genon Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour) Research Centre Jülich Jülich Germany. elinicolaisen@***. Centre for Medical Image Computing Department of Computer Science University College London London UK. Max Planck University College London Centre for Computational Psychiatry and Ageing Research University College London London UK. Department of Psychiatry University of Cambridge Cambridge UK. Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour) Research Centre Jülich Jülich Germany. Institute of Systems Neuroscience Heinrich Heine University Düsseldorf Düsseldorf Germany. Mathematical Institute Heinrich Heine University Düsseldorf Düsseldorf Germany. Otto Hahn Research Group "Cognitive Neurogenetics" Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany. Department of Electrical and Computer Engineering Centre for Translational MR Research Centre for Sleep & Cognition N.1 Institute for Health Institute for Digital Medicine National University of Singapore Singapore Singapore. Institute of Neuroscience and Medicine (INM-7: Brain and Behaviour) Research Centre Jülich Jülich Germany. s.genon@fz-juelich.de. Institute of Systems Neuroscience Heinrich Heine University Düsseldorf Düsseldorf Germany. s.genon@fz-juelich.de.

来源：评论

学校读者我要写书评

暂无评论

Deep learning based phase reconstruction for speaker separation: A trigonometric perspective

arXiv

引用

arXiv 2018年

作者： Wang, Zhong-Qiu Tan, Ke Wang, DeLiang Department of Computer Science and Engineering Ohio State University United States Center for Cognitive and Brain Sciences Ohio State University United States

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their magnitudes accurately estimated and under a geometric constraint, the absolute phase difference between each source and the mixture can be uniquely determined;in addition, the source phases at each time-frequency (T-F) unit can be narrowed down to only two candidates. To pick the right candidate, we propose three algorithms based on iterative phase reconstruction, group delay estimation, and phase-difference sign prediction. State-of-the-art results are obtained on the publicly available wsj0-2mix and 3mix corpus. Copyright © 2018, The Authors. All rights reserved.

关键词： Group delay

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Dissemination in time and space in presymptomatic granulin mutation carriers: A spatial chronnectome study" [Neurobiology of Aging Volume 108, December 2021, Pages 155-167]

引用

Neurobiology of aging 2022年 119卷 140-144页

作者： Enrico Premi Marcello Giunta Armin Iraji Srinivas Rachakonda VinceD Calhoun Stefano Gazzina Alberto Benussi Roberto Gasparotti Silvana Archetti Martina Bocchetta Dave Cash Emily Todd Georgia Peakman Rhian Convery John C van Swieten Lize Jiskoot Raquel Sanchez-Valle Fermin Moreno Robert Laforce Caroline Graff Matthis Synofzik Daniela Galimberti JamesB Rowe Mario Masellis Carmela Tartaglia Elizabeth Finger Rik Vandenberghe Alexandre de Mendonça Fabrizio Tagliavini Chris R Butler Isabel Santana Alexander Gerhard Isabelle Le Ber Florence Pasquier Simon Ducharme Johannes Levin Adrian Danek Sandro Sorbi Markus Otto Jonathan D Rohrer Barbara Borroni Stroke Unit Azienda Socio Sanitaria Territoriale Spedali Civili Brescia Brescia Italy. Centre for Neurodegenerative Disorders Department of Clinical and Experimental Sciences University of Brescia Brescia Italy. Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology Emory University Atlanta GA USA. Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) Georgia State University Georgia Institute of Technology Emory University Atlanta GA USA Departments of Psychology and Computer Science Georgia State University Atlanta GA USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA. Neurophysiology Unit Azienda Socio Sanitaria Territoriale Spedali Civili Brescia Brescia Italy. Neuroradiology Unit University of Brescia Brescia Italy. Laboratory Unit Azienda Socio Sanitaria Territoriale Spedali Civili Brescia Brescia Italy. Department of Neurodegenerative Disease Dementia Research Centre UCL Institute of Neurology Queen Square London UK. Department of Neurology Erasmus Medical Centre Rotterdam the Netherlands. Alzheimer's disease and Other Cognitive Disorders Unit Neurology Service Hospital Clinic University of Barcelona Barcelona Spain. Cognitive Disorders Unit Department of Neurology Donostia University Hospital San Sebastian Gipuzkoa Spain. Clinique Interdisciplinaire de Memoire Department des Sciences Neurologiques CHU de Quebec and Faculte de Medecine Universite Laval Quebec Canada. Center for Alzheimer Research Division of Neurogeriatrics Department of Neurobiology Care Sciences and Society Bioclinicum Karolinska Institutet Solna Sweden. Department of Neurodegenerative Diseases Hertie-Institute for Clinical Brain Research and Center of Neurology University of Tubingen Tubingen Germany. Fondazione Ca' Granda IRCCS Ospedale Policlinico Milan Italy University of Milan

来源：评论

学校读者我要写书评

暂无评论

Color naming reflects both perceptual structure and communicative need 40

Color naming reflects both perceptual structure and communic...

引用

40th Annual Meeting of the cognitive science Society: Changing Minds, CogSci 2018

作者： Zaslavsky, Noga Kemp, Charles Tishby, Naftali Regier, Terry Edmond and Lily Safra Centre for Brain Sciences The Hebrew University Jerusalem9190401 Israel Department of Psychology Carnegie Mellon University PittsburghPA15213 United States The Benin School of Computer Science and Engineering The Hebrew University Jerusalem9190401 Israel Department of Linguistics University of California BerkeleyCA94720 United States Cognitive Science Program University of California BerkeleyCA94720 United States

ISBN: (纸本)9780991196784

Gibson et al. (2017) argued that color naming is shaped by patterns of communicative need. In support of this claim, they showed that color naming systems across languages support more precise communication about warm colors than cool colors, and that the objects we talk about tend to be warm-colored rather than cool-colored. Here, we present new analyses that alter this picture. We show that greater communicative precision for warm than for cool colors, and greater communicative need, may both be explained by perceptual structure. However, using an information-theoretic analysis, we also show that color naming across languages bears signs of communicative need beyond what would be predicted by perceptual structure alone. We conclude that color naming is shaped both by perceptual structure, as has traditionally been argued, and by patterns of communicative need, as argued by Gibson et al. - although for reasons other than those they advanced. © 2018 Proceedings of the 40th Annual Meeting of the cognitive science Society, CogSci 2018. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Information-theoretic efficiency and semantic variation: The case of color naming 40

Information-theoretic efficiency and semantic variation: The...

引用

40th Annual Meeting of the cognitive science Society: Changing Minds, CogSci 2018

作者： Zaslavsky, Noga Kemp, Charles Regier, Terry Tishby, Naftali Edmond and Lily Safra Centre for Brain Sciences The Hebrew University Jerusalem9190401 Israel Department of Psychology Carnegie Mellon University PittsburghPA15213 United States Department of Linguistics University of California BerkeleyCA94720 United States Cognitive Science Program University of California BerkeleyCA94720 United States The Benin School of Computer Science and Engineering The Hebrew University Jerusalem9190401 Israel

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：