1 resultado para transcripts
em Massachusetts Institute of Technology
Filtro por publicador
- ABACUS. Repositorio de Producción Científica - Universidad Europea (1)
- Abertay Research Collections - Abertay University’s repository (2)
- Aberystwyth University Repository - Reino Unido (2)
- Aquatic Commons (2)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (5)
- Aston University Research Archive (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (6)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (26)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (2)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (13)
- Boston University Digital Common (1)
- Brock University, Canada (21)
- CaltechTHESIS (8)
- Cambridge University Engineering Department Publications Database (3)
- CentAUR: Central Archive University of Reading - UK (59)
- Center for Jewish History Digital Collections (5)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (93)
- Cochin University of Science & Technology (CUSAT), India (4)
- CORA - Cork Open Research Archive - University College Cork - Ireland (7)
- Dalarna University College Electronic Archive (3)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (3)
- DigitalCommons@The Texas Medical Center (2)
- Duke University (8)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (6)
- Greenwich Academic Literature Archive - UK (5)
- Harvard University (2)
- Helda - Digital Repository of University of Helsinki (32)
- Indian Institute of Science - Bangalore - Índia (34)
- Massachusetts Institute of Technology (1)
- Memorial University Research Repository (1)
- Ministerio de Cultura, Spain (1)
- National Center for Biotechnology Information - NCBI (30)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (2)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (91)
- Queensland University of Technology - ePrints Archive (166)
- Repositório digital da Fundação Getúlio Vargas - FGV (3)
- Repositório do Centro Hospitalar de Lisboa Central, EPE - Centro Hospitalar de Lisboa Central, EPE, Portugal (1)
- Repositorio Institucional de la Universidad Pública de Navarra - Espanha (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (100)
- Research Open Access Repository of the University of East London. (1)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (3)
- SAPIENTIA - Universidade do Algarve - Portugal (5)
- School of Medicine, Washington University, United States (1)
- SerWisS - Server für Wissenschaftliche Schriften der Fachhochschule Hannover (1)
- Universidad del Rosario, Colombia (3)
- Universidade de Lisboa - Repositório Aberto (4)
- Universidade Federal do Pará (3)
- Universidade Federal do Rio Grande do Norte (UFRN) (7)
- Universitat de Girona, Spain (1)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (3)
- Université de Lausanne, Switzerland (8)
- Université de Montréal, Canada (54)
- Université Laval Mémoires et thèses électroniques (1)
- University of Michigan (11)
- University of Queensland eSpace - Australia (8)
- University of Southampton, United Kingdom (3)
- WestminsterResearch - UK (1)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
We present an unsupervised learning algorithm that acquires a natural-language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of language that overcomes many of the problems that have stymied previous grammar-induction procedures. The forward mapping from symbol sequences to the speech stream is modeled using features based on articulatory gestures. We present results on the acquisition of lexicons and language models from raw speech, text, and phonetic transcripts, and demonstrate that our algorithm compares very favorably to other reported results with respect to segmentation performance and statistical efficiency.