检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Atta Norouzian Richard Rose Sina Hamidi Ghalehjegh Aren Jansen Department of Electrical and Computer Engineering McGill University Montreal Canada Human Language Technology Center of Excellence Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA

ISBN: (纸本)9781479903573

In this paper the use of acoustic similarity of speech intervals for generating improved confidence scores for spoken term detection (STD) is investigated. A procedure based on acoustic dotplots which requires no training data is deployed for discovering similar speech intervals. A graph based random walk algorithm incorporates acoustic similarity of hypothesized term occurrences for improving the corresponding confidence scores. The proposed approach is evaluated in an open vocabulary STD task defined on a lecture domain corpus. It is shown that updating the confidence scores in this fashion results in a significant increase in term detection performance of out of vocabulary search terms. A relative improvement of 12.9% in figure of merit was gained relative to that obtained from a baseline lattice based STD system.

关键词： Acoustics Speech Lattices Acoustic measurements Vectors Vocabulary Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Mandarin-English Code-Switching Corpus 8

A Mandarin-English Code-Switching Corpus

引用

8th International Conference on language Resources and Evaluation (LREC)

作者： Li, Ying Yu, Yue Fung, Pascale Human Language Technology Center Department of Electronic and Computer Engineering HKUST Hong Kong

ISBN: (纸本)9782951740877

Generally the existing monolingual corpora are not suitable for large vocabulary continuous speech recognition (LVCSR) of code-switching speech. The motivation of this paper is to study the rules and constraints code-switching follows and design a corpus for code-switching LVCSR task. This paper presents the development of a Mandarin-English code-switching corpus. This corpus consists of four parts: 1) conversational meeting speech and its data;2) project meeting speech data;3) student interviews speech;4) text data of on-line news. The speech was transcribed by an annotator and verified by Mandarin-English bilingual speakers manually. We propose an approach for automatically downloading from the web text data that contains code-switching. The corpus includes both intra-sentential code-switching (switch in the middle of a sentence) and inter-sentential code-switching (switch at the end of the sentence). The distribution of part-of-speech (POS) tags and code-switching reasons are reported.

关键词： code-switch code-mix mixed language

来源：评论

学校读者我要写书评

暂无评论

Code-switch language model with inversion constraints for mixed language speech recognition

Code-switch language model with inversion constraints for mi...

引用

24th International Conference on Computational Linguistics, COLING 2012

作者： Li, Ying Fung, Pascale Department of Electronic and Computer Engineering Human Language Technology Center Hong Kong

We propose a first ever code-switch language model for mixed language speech recognition that incorporates syntactic constraints by a code-switch boundary prediction model, a code-switch translation model, and a reconstruction model. A WFST-based decoder then recognizes speech by combining an acoustic model, a pronunciation model and the code-switch language model in an integrated approach. Our proposed approach avoids making early decisions on code-switch boundaries and is therefore more robust than previous approaches. Our proposed system using the code-switch language model outperforms a baseline of interpolated language models by a statistically significant 0.91% on a mixed language lecture speech corpus, and 1.25% on a mixed language lunch conversation corpus. Our method also outperforms a language model that permits code-switch at all word boundaries by a statistically significant 1.35% on the lecture speech corpus and 1.69% on the lunch conversation corpus. © 2012 The COLING.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Poster abstracts

引用

Sleep and Biological Rhythms 2016年第1期5卷 A1-A189页

作者： J. Ferrie M. Shipley F. Cappuccio E. Brunner M. Miller M. Kumari M. Marmot A. Coenen J. L. Castillo F. Araya G. Bustamante L. Montecino C. Torres S. Oporto J. Gronli E. Fiske R. Murison B. Bjorvatn E. Sorensen R. Ursin C. M. Portas S. Rajaraman A. Gribok N. Wesensten T. Balkin J. Reifman N. Dursunoglu S. Ozkurt S. Baser O. Delen S. Sarikaya P. Sadler P. Mitchell D. Françon M. Decobert B. Herve A. Richard G. Griebel P. Avenet B. Scatton G. L. Fur D. Eckert A. Jordan A. Wellman S. Smith A. Malhotra D. White D. Bruck I. Thomas A. Kritikos W. Oertel K. Stiasny-Kolster D. Garcia-Borreguero W. Poewe B. Hoegl R. Kohnen E. Schollmayer J. Keffel C. Trenkwalder A. Valle S. Roizenblatt F. Fregni P. Boggio S. Tufik K. Ward L. Robertson L. Palmer P. Eastwood D. Hillman J. Lee S. Mukherjee V. de Padova G. Barbato G. Ficca I. Zilli P. Salzarulo M. Veldi T. Hion V. Vasar M. Kull L. Nowak J. Davis Y. Latzer O. Tzischinsky S. Crowley M. Carskadon M. Anca-Herschkovitsch D. Frey J. Ortega C. Wiseman C. Farley K. Wright A. Campbell A. Neill K. Spiegel R. Leproult E. Tasali N. Scherberg E. van Cauter A. T. Noradina N. A. Karim I. Norlinah A. A. Raymond R. Sahathevan B. Hamidon E. Werth R. Poryazova R. Khatami C. Bassetti R. G. Beran L. Ainley G. Holand J. Duncan H. Kinney B. Davis B. Hood S. Frey C. Schmidt M. Hofstetter P. Peigneux C. Cajochen W.-P. Hu J.-D. Li C. Zhang L. Boehmer J. Siegel Q.-Y. Zhou Y. Sagawa H. Kondo T. Takemura H. Kanayama Y. Kaneko M. Sato T. Kanbayashi Y. Hishikawa T. Shimizu A. Viola L. James L. Schlangen D.-J. Dijk R. Andretic Y.-C. Kim K.-A. Han F. Jones R. Greenspan L. Sanford L. Yang X. Tang K. Dieter E. Uta H. Sven M. Richard N. Oyane S. Pallesen F. Holsten Y. Inoue M. Fujita N. Emura K. Kuroda N. Uchimura A. Johnston J. Astbury G. Kennedy K. Hoedlmoser M. Schabus T. Pecherstorfer S. Moser G. Gruber P. Anderer W. Klimesch N. Naidoo M. Ferber A. Pack D. Neu O. Mairesse G. Hoffmann A. Dris L. Lambrecht P. Linkowski P. Verbanck O. Le Bon N. Matsuura M. Yamao N. Adachi R. Aritomi Y. Komada H. Tanaka S. Shirak University College London London UK University College London London USA Warwick Medical School London UK Warwick Medical School Coventry USA Radboud University Nijmegen Nijmegen Netherlands Department of Neurology University of Chile Santiago Chile Neurology Service Hospital del Salvador Santiago Chile Family Health Center Juan Pablo II Santiago Chile Department of Biomedicine Section on Physiology Univeristy of Bergen Bergen Norway Department of Public Health and Primary Health Care Univeristy of Bergen Bergen Norway Department of Public Health and Primary Health Care University of Bergen Bergen Norway Norwegian Competence Center for Sleep Disorders Haukeland University Hospital Bergen Norway Department of Child and Adolescent Psychiatry Haukeland University Hospital Univeristy of Bergen Bergen Norway Department of Biomedicine University of Bergen Bergen Norway US Army Medical Research and Materiel Command Fort Detrick Frederick USA Walter Reed Army Institute of Research Silver Spring USA Department of Behavioral Biology Walter Reed Army Institute of Research Silver Spring USA Faculty Department of Pulmonology Pamukkale University Medical Denizli Turkey University of Ballarat Ballarat Australia Sanofi-Aventis Recherche et Developpement Paris France Brigham and Women’s Hospital Harvard Medical School Boston USA The University of Queensland Adelaide Australia School of Psychology University of Queensland Brisbane Australia The University of Queensland Brisbane Australia Victoria University Melbourne Australia Department of Psychology Victoria University Melbourne Australia School of Psychology Victoria University Melbourne Australia Philips-Universität Marburg Germany Philips-Universitaet-Marburg Marburg Germany Instituto de Investigaciones del Sueno Madrid Spain Universitätsklinik für Neurologie Innsbruck Austria Universitaetsklinik fuer Neurologie Innsbruck Austria IMEREM GmbH Nuernberg Germany Schwarz Pharma AG Monheim Germany

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual language modeling with syntactic reordering for low-resource speech recognition

Cross-Lingual language modeling with syntactic reordering fo...

引用

2012 Joint Conference on Empirical Methods in Natural language Processing and Computational Natural language Learning, EMNLP-CoNLL 2012

作者： Xu, Ping Fung, Pascale Human Language Technology Center Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong Hong Kong

ISBN: (纸本)9781937284435

This paper proposes cross-lingual language modeling for transcribing source resource-poor languages and translating them into target resource-rich languages if necessary. Our focus is to improve the speech recognition performance of low-resource languages by leveraging the language model statistics from resource-rich languages. The most challenging work of cross-lingual language modeling is to solve the syntactic discrepancies between the source and target languages. We therefore propose syntactic reordering for cross-lingual language modeling, and present a first result that compares inversion transduction grammar (ITG) reordering constraints to IBM and local constraints in an integrated speech transcription and translation system. Evaluations on resource-poor Cantonese speech transcription and Cantonese to resource-rich Mandarin translation tasks show that our proposed approach improves the system performance significantly, up to 3.4% relative WER reduction in Cantonese transcription and 13.3% relative bilingual evaluation understudy (BLEU) score improvement in Mandarin transcription compared with the system without reordering. © 2012 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Fully Automatic Semantic MT Evaluation 7

Fully Automatic Semantic MT Evaluation

引用

7th Workshop on Statistical Machine Translation, WMT 2012, immediately following the Conference of the North-American Chapter of the Association for Computational Linguistics - human language Technologies, NAACL HLT 2012

作者： Lo, Chi-Kiu Tumuluru, Anand Karthik Wu, Dekai Hkust Human Language Technology Center Department Of Computer Science And Engineering Hong Kong University Of Science And Technology Hong Kong

ISBN: (纸本)9781937284206

We introduce the first fully automatic, fully semantic frame based MT evaluation metric, MEANT, that outperforms all other commonly used automatic metrics in correlating with human judgment on translation adequacy. Recent work on HMEANT, which is a human metric, indicates that machine translation can be better evaluated via semantic frames than other evaluation paradigms, requiring only minimal effort from monolingual humans to annotate and align semantic frames in the reference and machine translations. We propose a surprisingly effective Occam's razor automation of HMEANT that combines standard shallow semantic parsing with a simple maximum weighted bipartite matching algorithm for aligning semantic frames. The matching criterion is based on lexical similarity scoring of the semantic role fillers through a simple context vector model which can readily be trained using any publicly available large monolingual corpus. Sentence level correlation analysis, following standard NIST MetricsMATR protocol, shows that this fully automated version of HMEANT achieves significantly higher Kendall correlation with human adequacy judgments than BLEU, NIST, METEOR, PER, CDER, WER, or TER. Furthermore, we demonstrate that performing the semantic frame alignment automatically actually tends to be just as good as performing it manually. Despite its high performance, fully automated MEANT is still able to preserve HMEANT's virtues of simplicity, representational transparency, and inexpensiveness. ©2012 Association for Computational Linguistics.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised vs. supervised weight estimation for semantic MT evaluation metrics 6

Unsupervised vs. supervised weight estimation for semantic M...

引用

6th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2012 at the 50th Annual Meeting of the Association for Computational Linguistics, ACT 2012

作者： Lo, Chi-Kiu Wu, Dekai HKUST Human Language Technology Center Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9781937284381

We present an unsupervised approach to estimate the appropriate degree of contribution of each semantic role type for semantic translation evaluation, yielding a semantic MT evaluation metric whose correlation with human adequacy judgments is comparable to that of recent supervised approaches but without the high cost of a human-ranked training corpus. Our new unsupervised estimation approach is motivated by an analysis showing that the weights learned from supervised training are distributed in a similar fashion to the relative frequencies of the semantic roles. Empirical results show that even without a training corpus of human adequacy rankings against which to optimize correlation, using instead our relative frequency weighting scheme to approximate the importance of each semantic role type leads to a semantic MT evaluation metric that correlates comparable with human adequacy judgments to previous metrics that require far more expensive human rankings of adequacy over a training corpus. As a result, the cost of semantic MT evaluation is greatly reduced. © 2012 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptation transforms of auto-associative neural networks as features for speaker verification

Adaptation transforms of auto-associative neural networks as...

引用

Speaker and language Recognition Workshop, Odyssey 2012

作者： Thomas, Samuel Mallidi, Sri Harish Ganapathy, Sriram Hermansky, Hynek Center for Language and Speech Processing Department of Electrical and Computer Engineering Johns Hopkins University Baltimore United States Human Language Technology Center of Excellence Johns Hopkins University Baltimore United States

ISBN: (纸本)9789810730932

We present a new approach of using Auto-Associative Neural Networks (AANNs) in the conventional GMM speaker verification framework with i-vector feature extraction and PLDA modeling. In this technique, an i-vector feature extractor is trained using adaptation parameters from a mixture of AANNs. In order to model parts of each speaker's acoustic space, a training objective function based on posterior probabilities of broad phonetic classes is used. The AANN based i-vectors are fused with GMM based i-vectors and a joint PLDA model is trained. The proposed approach provides promising results and significant gains when combined with baseline systems on the telephone conditions of NIST SRE 2010 and the recently concluded IARPA BEST 2011 speaker evaluations. © Odyssey 2012 - Speaker and language Recognition Workshop. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

RESOURCE DEVELOPMENT AND EXPERIMENTS IN AUTOMATIC SOUTH AFRICAN BROADCAST NEWS TRANSCRIPTION 3

RESOURCE DEVELOPMENT AND EXPERIMENTS IN AUTOMATIC SOUTH AFRI...

引用

3rd Workshop on Spoken language Technologies for Under-Resourced languages, SLTU 2012

作者： Kamper, Herman de Wet, Febe Hain, Thomas Niesler, Thomas Department of Electrical and Electronic Engineering Stellenbosch University South Africa Human Language Technology Competency Area CSIR Meraka Institute Pretoria South Africa Department of Computer Science University of Sheffield United Kingdom

We present a description of the development and evaluation of a first South African broadcast news transcription system. We describe a number of speech resources which have been collected in the resource-scarce South African environment for system development purposes: a 20 hour corpus of South African English (SAE) broadcast news;a 109M word corpus of South African newspaper text collected for language modelling purposes;and a 60k word SAE pronunciation dictionary. The development of our system is based on similar state-of-the-art broadcast news transcription systems and uses cross-word triphone HMMs, MF-PLP features and per-segment cepstral mean and per-bulletin cepstral variance normalisation. Our final system achieves a word error rate of 24.6%. We find that reasonable performance is achieved on newsreader speech while poor performance is achieved on spontaneous and telephone speech in our test data. Finally, we consider the recognition of MP3-compressed audio and show that performance deteriorates only at low bit-rates. © SLTU 2012. All Rights Reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Lowresource speech recognition with automatically learned sparse inverse covariance matrices

Lowresource speech recognition with automatically learned sp...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Weibin Zhang Pascale Fung HKUST Human Language Technology Center Department of Electronic and Computer Engineering University of Science and Technology (HKUST) Hong Kong China

Full covariance acoustic models trained with limited training data generalize poorly to unseen test data due to a large number of free parameters. We propose to use sparse inverse covariance matrices to address this problem. Previous sparse inverse covariance methods never outperformed full covariance methods. We propose a method to automatically drive the structure of inverse covariance matrices to sparse during training. We use a new objective function by adding L1 regularization to the traditional objective function for maximum likelihood estimation. The graphic lasso method for the estimation of a sparse inverse covariance matrix is incorporated into the Expectation Maximization algorithm to learn parameters of HMM using the new objective function. Experimental results show that we only need about 25% of the parameters of the inverse covariance matrices to be nonzero in order to achieve the same performance of a full covariance system. Our proposed system using sparse inverse covariance Gaussians also significantly outperforms a system using full covariance Gaussians trained on limited data.

关键词： Covariance matrix Hidden Markov models Training data Linear programming Sparse matrices Training Maximum likelihood estimation

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：