Word Learning Prosodic Information by Berndt Daniel (4 results)
- More images
- Softcover
Seller: preigu, Osnabrück, Germanypreigu
Contact seller5-star sellerCondition: New
£ 38.26
£ 59.99 shippingShips from Germany to U.S.A.Quantity: 5 available
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[a…t]preigu[dot]de | Anbieter: preigu.
- Softcover
Seller: Mispah books, Redhill, SURRE, United KingdomMispah books
Contact seller4-star sellerCondition: New
£ 145.00
£ 25.00 shippingShips from United Kingdom to U.S.A.Quantity: 1 available
paperback. Condition: New. NEW. SHIPS FROM MULTIPLE LOCATIONS. book.
- More images
- Softcover
- Print on Demand
Seller: moluna, Greven, Germanymoluna
Contact seller5-star sellerCondition: New
£ 34.64
£ 41.98 shippingShips from Germany to U.S.A.Quantity: Over 20 available
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 dev…eloping company applying techniques from AI and Computa.
- More images
- Softcover
- Print on Demand
Seller: AHA-BUCH GmbH, Einbeck, GermanyAHA-BUCH GmbH
Contact seller5-star sellerCondition: New
£ 43.77
£ 52.05 shippingShips from Germany to U.S.A.Quantity: 2 available
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 pair…ed 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.
