Statistical Pronunciation Modeling for Non-Native Speech Processing [electronic resource] / by Rainer E. Gruhn, Wolfgang Minker, Satoshi Nakamura.
Tipo de material: TextoSeries Signals and Communication Technology; Descripción: X, 114 p. online resourceISBN: 9783642195860 99783642195860Tema(s): Engineering | Engineering | PHONOLOGY | PHONOLOGY | LANGUAGE TRANSLATION AND LINGUISTICS | TRANSLATORS (COMPUTER PROGRAMS) | SIGNAL, IMAGE AND SPEECH PROCESSING | STATICS FOR ENGINEERING, PHYSICS, COMPUTERS SCIENCE, CHEMISTRY AND EARTH SCIENCESClasificación CDD: 621.382 Recursos en línea: ir a documentoTipo de ítem | Ubicación actual | Colección | Signatura | Info Vol | Copia número | Estado | Fecha de vencimiento | Código de barras | Reserva de ítems |
---|---|---|---|---|---|---|---|---|---|
DOCUMENTOS DIGITALES | Biblioteca Jorge Álvarez Lleras | Digital | 621.382 223 (Navegar estantería) | Ej. 1 | 1 | Disponible | D000715 |
Navegando Biblioteca Jorge Álvarez Lleras Estantes, Código de colección: Digital Cerrar el navegador de estanterías
621.382 223 Sensor Networks with IEEE 802.15.4 Systems | 621.382 223 OFDM | 621.382 223 Integral and Diagnostic Intrusive Prediction of Speech Quality | 621.382 223 Statistical Pronunciation Modeling for Non-Native Speech Processing | 621.382 223 Optimal Time-Domain Noise Reduction Filters | 621.382 223 The Sound of Silence | 621.382 223 On the Achievable Rate of Stationary Fading Channels |
Introduction -- Automatic Speech Recognition -- Properties of Non-native Speech -- Pronunciation Variation Modeling in the Literature -- Non-native Speech Database -- Handling Non-native Speech -- Pronunciation HMMs.
In this work, the authors present a fully statistical approach to model non--native speakers' pronunciation. Second-language speakers pronounce words in multiple different ways compared to the native speakers. Those deviations, may it be phoneme substitutions, deletions or insertions, can be modelled automatically with the new method presented here. The methods is based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary. The implementation and functionality of the methodology has been proven and verified with a test set of non-native English in the regarding accent. The book is written for researchers with a professional interest in phonetics and automatic speech and speaker recognition.
No hay comentarios en este titulo.