Automatic translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules such as automatic speech recognition (ASR) and machine translation (MT) systems. In recent years, statistical approaches to both ASR and MT were proven to be effective on a large number of translation tasks. Yet the systems involved in speech translation are often developed independently of each other. This work explains how a significant improvement of speech translation quality can be obtained by enhancing the interface between various statistical NLP systems involved in the task of translating human speech. The whole pipeline is considered: ASR, automatic sentence segmentation, machine translation using several systems which take single best or multiple ASR hypotheses as input and employ different translation models, combination of different MT systems. The coupling between the various components is reached through combination of model scores and/or hypotheses as well as through development of new and modifications of existing algorithms to handle ambiguous input or to meet the constraints of the downstream components.
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
Evgeny Matusov defended his Ph.D. in computer science from RWTHAachen University, Germany in 2009. His research interest ismachine translation of text and speech. He authored andco-authored more than 20 reviewed publications in internationalconferences, two journal publications, and received the ISCA BestStudent Paper Award in 2005.
„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.
Anbieter: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Deutschland
Taschenbuch. Zustand: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Automatic translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules such as automatic speech recognition (ASR) and machine translation (MT) systems. In recent years, statistical approaches to both ASR and MT were proven to be effective on a large number of translation tasks. Yet the systems involved in speech translation are often developed independently of each other. This work explains how a significant improvement of speech translation quality can be obtained by enhancing the interface between various statistical NLP systems involved in the task of translating human speech. The whole pipeline is considered: ASR, automatic sentence segmentation, machine translation using several systems which take single best or multiple ASR hypotheses as input and employ different translation models, combination of different MT systems. The coupling between the various components is reached through combination of model scores and/or hypotheses as well as through development of new and modifications of existing algorithms to handle ambiguous input or to meet the constraints of the downstream components. 236 pp. Englisch. Bestandsnummer des Verkäufers 9783838120126
Anzahl: 2 verfügbar
Anbieter: moluna, Greven, Deutschland
Zustand: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Matusov EvgenyEvgeny Matusov defended his Ph.D. in computer science from RWTHAachen University, Germany in 2009. His research interest ismachine translation of text and speech. He authored andco-authored more than 20 reviewed publica. Bestandsnummer des Verkäufers 5406366
Anzahl: Mehr als 20 verfügbar
Anbieter: preigu, Osnabrück, Deutschland
Taschenbuch. Zustand: Neu. Advantages of System Combination for Spoken Language Translation | Combining Natural Language Processing Systems to Improve Machine Translation of Speech | Evgeny Matusov | Taschenbuch | 236 S. | Englisch | 2015 | Südwestdeutscher Verlag für Hochschulschriften | EAN 9783838120126 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu. Bestandsnummer des Verkäufers 107275222
Anzahl: 5 verfügbar
Anbieter: buchversandmimpf2000, Emtmannsberg, BAYE, Deutschland
Taschenbuch. Zustand: Neu. This item is printed on demand - Print on Demand Titel. Neuware -Automatic translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules such as automatic speech recognition (ASR) and machine translation (MT) systems. In recent years, statistical approaches to both ASR and MT were proven to be effective on a large number of translation tasks. Yet the systems involved in speech translation are often developed independently of each other. This work explains how a significant improvement of speech translation quality can be obtained by enhancing the interface between various statistical NLP systems involved in the task of translating human speech. The whole pipeline is considered: ASR, automatic sentence segmentation, machine translation using several systems which take single best or multiple ASR hypotheses as input and employ different translation models, combination of different MT systems. The coupling between the various components is reached through combination of model scores and/or hypotheses as well as through development of new and modifications of existing algorithms to handle ambiguous input or to meet the constraints of the downstream components.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 236 pp. Englisch. Bestandsnummer des Verkäufers 9783838120126
Anzahl: 1 verfügbar
Anbieter: AHA-BUCH GmbH, Einbeck, Deutschland
Taschenbuch. Zustand: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - Automatic translation of spoken language is a challenging task that involves several natural language processing (NLP) software modules such as automatic speech recognition (ASR) and machine translation (MT) systems. In recent years, statistical approaches to both ASR and MT were proven to be effective on a large number of translation tasks. Yet the systems involved in speech translation are often developed independently of each other. This work explains how a significant improvement of speech translation quality can be obtained by enhancing the interface between various statistical NLP systems involved in the task of translating human speech. The whole pipeline is considered: ASR, automatic sentence segmentation, machine translation using several systems which take single best or multiple ASR hypotheses as input and employ different translation models, combination of different MT systems. The coupling between the various components is reached through combination of model scores and/or hypotheses as well as through development of new and modifications of existing algorithms to handle ambiguous input or to meet the constraints of the downstream components. Bestandsnummer des Verkäufers 9783838120126
Anzahl: 1 verfügbar