Word Learning with Prosodic information: Applying non-verbal Cues to enhance Speech Recognition Performance - Brossura

Berndt, Daniel

Brossura

ISBN 10: 363931414X ISBN 13: 9783639314144

Casa editrice: VDM Verlag Dr. Müller, 2010

Riassunto

Previous studies have shown that infants use prosodic information as an aid for discriminating and recognising words. The present work is based on a word learning model which automatically extracts target words from raw speech input paired with a label for the target word. This model was enhanced by incorporating prosodic information. In addition, an unsupervised model is developed which does not rely on a label of any kind. Although prosodic information could not improve the performance of the unsupervised model, it is shown that the incorporation of pitch leads to an increase of performance in the supervised case and that the unsupervised model yields effective results.

Su questo libro

L'autore

Born 1988 in Rostock, Germany, Daniel Berndt studied Cognitive Science in Osnabrück and Artificial Intelligence in Edinburgh. He became co-founder of Codeus, a developing company applying techniques from AI and Computational Linguistics and continues to work in his field of interest.

Dettagli dell'edizione

• Editore: VDM Verlag Dr. Müller
• Data di pubblicazione: 2010
• Lingua: Inglese
• ISBN 10: 363931414X
• ISBN 13: 9783639314144
• Rilegatura: Copertina flessibile
• Numero di pagine: 88
• Contatto del produttore: non disponibile
• Persona responsabile: non disponibile