Word Learning with Prosodic information: Applying non-verbal Cues to enhance Speech Recognition Performance - Softcover
Synopsis
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.
"synopsis" may belong to another edition of this title.
About the Author
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.
"About this title" may belong to another edition of this title.
Search results for Word Learning with Prosodic information: Applying non-verbal...
Seller Image
Word Learning with Prosodic information
Published by
VDM Verlag Dr. Müller, 2010
ISBN 10: 363931414X
ISBN 13: 9783639314144
New
Kartoniert / Broschiert
Seller: moluna, Greven, Germany
Seller rating 5 out of 5 stars
Kartoniert / Broschiert. Condition: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Berndt DanielBorn 1988 in Rostock, Germany, Daniel Berndt studied Cognitive Science in Osnabrueck and Artificial Intelligence in Edinburgh. He became co-founder of Codeus, a developing company applying techniques from AI and Computa. Seller Inventory # 4976750
Buy New
£ 34.87
£ 42.26 shipping
Ships from Germany to U.S.A.
Ships from Germany to U.S.A.
Quantity: Over 20 available
Seller Image
Word Learning with Prosodic information : Applying non-verbal Cues to enhance Speech Recognition Performance
Print on DemandSeller: AHA-BUCH GmbH, Einbeck, Germany
Seller rating 5 out of 5 stars
Taschenbuch. Condition: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - 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. Seller Inventory # 9783639314144
Seller Image
Word Learning with Prosodic information | Applying non-verbal Cues to enhance Speech Recognition Performance
Seller: preigu, Osnabrück, Germany
Seller rating 5 out of 5 stars
Taschenbuch. Condition: Neu. Word Learning with Prosodic information | Applying non-verbal Cues to enhance Speech Recognition Performance | Daniel Berndt | Taschenbuch | Englisch | VDM Verlag Dr. Müller | EAN 9783639314144 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu. Seller Inventory # 107175266
Stock Image
Word Learning with Prosodic information: Applying non-verbal Cues to enhance Speech Recognition Performance
Seller: Mispah books, Redhill, SURRE, United Kingdom
Seller rating 4 out of 5 stars
paperback. Condition: New. NEW. SHIPS FROM MULTIPLE LOCATIONS. book. Seller Inventory # ERICA829363931414X6