1 resultado para criticism of texts
em Cambridge University Engineering Department Publications Database
Filtro por publicador
- Aberystwyth University Repository - Reino Unido (4)
- Adam Mickiewicz University Repository (5)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (12)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (4)
- Andina Digital - Repositorio UASB-Digital - Universidade Andina Simón Bolívar (4)
- Aquatic Commons (2)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (1)
- Archive of European Integration (104)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (8)
- Aston University Research Archive (14)
- Biblioteca Digital | Sistema Integrado de Documentación | UNCuyo - UNCUYO. UNIVERSIDAD NACIONAL DE CUYO. (14)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (6)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (4)
- Biblioteca Digital de la Universidad Católica Argentina (6)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (50)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (14)
- Brock University, Canada (2)
- Bucknell University Digital Commons - Pensilvania - USA (1)
- Bulgarian Digital Mathematics Library at IMI-BAS (3)
- Cambridge University Engineering Department Publications Database (1)
- CentAUR: Central Archive University of Reading - UK (30)
- Center for Jewish History Digital Collections (3)
- Central European University - Research Support Scheme (3)
- Cochin University of Science & Technology (CUSAT), India (1)
- CORA - Cork Open Research Archive - University College Cork - Ireland (3)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (2)
- Dalarna University College Electronic Archive (7)
- Deakin Research Online - Australia (71)
- Digital Archives@Colby (1)
- Digital Commons - Michigan Tech (1)
- Digital Commons at Florida International University (3)
- DigitalCommons@The Texas Medical Center (1)
- DigitalCommons@University of Nebraska - Lincoln (1)
- Duke University (2)
- Harvard University (3)
- Helda - Digital Repository of University of Helsinki (29)
- Helvia: Repositorio Institucional de la Universidad de Córdoba (1)
- Indian Institute of Science - Bangalore - Índia (1)
- Instituto de Engenharia Nuclear, Brazil - Carpe dIEN (1)
- Instituto Politécnico do Porto, Portugal (3)
- Memoria Académica - FaHCE, UNLP - Argentina (47)
- Memorial University Research Repository (1)
- Ministerio de Cultura, Spain (1)
- Nottingham eTheses (3)
- Portal de Revistas Científicas Complutenses - Espanha (9)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (21)
- Queensland University of Technology - ePrints Archive (55)
- RDBU - Repositório Digital da Biblioteca da Unisinos (1)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (4)
- Repositório Científico da Universidade de Évora - Portugal (2)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (8)
- Repositório digital da Fundação Getúlio Vargas - FGV (14)
- Repositório Institucional da Universidade de Aveiro - Portugal (3)
- Repositório Institucional da Universidade Estadual de São Paulo - UNESP (3)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (196)
- SAPIENTIA - Universidade do Algarve - Portugal (1)
- Savoirs UdeS : plateforme de diffusion de la production intellectuelle de l’Université de Sherbrooke - Canada (1)
- School of Medicine, Washington University, United States (1)
- Universidad de Alicante (2)
- Universidad del Rosario, Colombia (2)
- Universidad Politécnica de Madrid (2)
- Universidade Complutense de Madrid (1)
- Universidade de Lisboa - Repositório Aberto (3)
- Universidade Federal do Pará (10)
- Universidade Federal do Rio Grande do Norte (UFRN) (30)
- Universidade Metodista de São Paulo (3)
- Universitat de Girona, Spain (2)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (1)
- Université de Montréal, Canada (43)
- University of Michigan (43)
- University of Queensland eSpace - Australia (6)
- University of Southampton, United Kingdom (5)
- University of Washington (1)
- WestminsterResearch - UK (2)
Resumo:
Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.