931 resultados para alternative modeling approaches
Filtro por publicador
- Aberystwyth University Repository - Reino Unido (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (10)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (2)
- Aquatic Commons (8)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (3)
- Archive of European Integration (1)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (3)
- Aston University Research Archive (22)
- B-Digital - Universidade Fernando Pessoa - Portugal (1)
- Biblioteca de Teses e Dissertações da USP (5)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (3)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (6)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (29)
- Boston University Digital Common (3)
- Brock University, Canada (1)
- Bulgarian Digital Mathematics Library at IMI-BAS (3)
- CaltechTHESIS (4)
- Cambridge University Engineering Department Publications Database (14)
- CentAUR: Central Archive University of Reading - UK (28)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (6)
- Cochin University of Science & Technology (CUSAT), India (1)
- Collection Of Biostatistics Research Archive (2)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (2)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (5)
- CUNY Academic Works (1)
- Dalarna University College Electronic Archive (2)
- Deakin Research Online - Australia (48)
- Department of Computer Science E-Repository - King's College London, Strand, London (1)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (1)
- Digital Commons - Michigan Tech (13)
- Digital Commons @ DU | University of Denver Research (1)
- Digital Commons at Florida International University (32)
- Digital Peer Publishing (1)
- DigitalCommons@The Texas Medical Center (8)
- DigitalCommons@University of Nebraska - Lincoln (3)
- Doria (National Library of Finland DSpace Services) - National Library of Finland, Finland (1)
- DRUM (Digital Repository at the University of Maryland) (6)
- Duke University (10)
- Ecology and Society (1)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (5)
- Glasgow Theses Service (1)
- Greenwich Academic Literature Archive - UK (5)
- Helda - Digital Repository of University of Helsinki (9)
- Illinois Digital Environment for Access to Learning and Scholarship Repository (2)
- Indian Institute of Science - Bangalore - Índia (13)
- Institutional Repository of Leibniz University Hannover (1)
- Instituto Gulbenkian de Ciência (2)
- Instituto Politécnico de Bragança (1)
- Instituto Politécnico do Porto, Portugal (1)
- Massachusetts Institute of Technology (2)
- Memorial University Research Repository (2)
- National Center for Biotechnology Information - NCBI (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (6)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- Publishing Network for Geoscientific & Environmental Data (2)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (34)
- Queensland University of Technology - ePrints Archive (399)
- Repositório Científico da Universidade de Évora - Portugal (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (6)
- Repositório Institucional da Universidade de Aveiro - Portugal (5)
- Repositorio Institucional de la Universidad de Málaga (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (34)
- Research Open Access Repository of the University of East London. (2)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (1)
- SAPIENTIA - Universidade do Algarve - Portugal (6)
- Scielo España (1)
- Universidad de Alicante (3)
- Universidad del Rosario, Colombia (3)
- Universidad Politécnica de Madrid (22)
- Universidade Complutense de Madrid (1)
- Universidade de Lisboa - Repositório Aberto (2)
- Universidade Federal do Pará (2)
- Universidade Federal do Rio Grande do Norte (UFRN) (2)
- Universita di Parma (1)
- Universitat de Girona, Spain (5)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (2)
- Université de Lausanne, Switzerland (1)
- Université de Montréal (1)
- Université de Montréal, Canada (7)
- Université Laval Mémoires et thèses électroniques (1)
- University of Connecticut - USA (1)
- University of Michigan (15)
- University of Queensland eSpace - Australia (16)
- University of Southampton, United Kingdom (1)
- University of Washington (6)
- WestminsterResearch - UK (2)
Resumo:
This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.