Matches in Harvard for { <http://id.lib.harvard.edu/aleph/009103801/catalog> ?p ?o. }
Showing items 1 to 28 of
28
with 100 items per page.
- catalog abstract "Speech recognition technology is being increasingly employed in human-machine interfaces. A remaining problem however is the robustness of this technology to non-native accents, which still cause considerable difficulties for current systems. In this book, methods to overcome this problem are described. A speaker adaptation algorithm that is capable of adapting to the current speaker with just a few words of speaker-specific data based on the MLLR principle is developed and combined with confidence measures that focus on phone durations as well as on acoustic features. Furthermore, a specific pronunciation modelling technique that allows the automatic derivation of non-native pronunciations without using non-native data is described and combined with the previous techniques to produce a robust adaptation to non-native accents in an automatic speech recognition system.".
- catalog contributor b12820142.
- catalog created "c2002.".
- catalog date "2002".
- catalog date "c2002.".
- catalog dateCopyrighted "c2002.".
- catalog description "ASR:AnOverview -- Pre-processing of the Speech Data -- Stochastic Modelling of Speech -- Knowledge Bases of an ASR System -- Speaker Adaptation -- Confidence Measures -- Pronunciation Adaptation -- Future Work -- Summary -- Databases and Experimental Settings -- MLLR Results -- Phoneme Inventory.".
- catalog description "Includes bibliographical references (p. [113]-123) and index.".
- catalog description "Speech recognition technology is being increasingly employed in human-machine interfaces. A remaining problem however is the robustness of this technology to non-native accents, which still cause considerable difficulties for current systems. In this book, methods to overcome this problem are described. A speaker adaptation algorithm that is capable of adapting to the current speaker with just a few words of speaker-specific data based on the MLLR principle is developed and combined with confidence measures that focus on phone durations as well as on acoustic features. Furthermore, a specific pronunciation modelling technique that allows the automatic derivation of non-native pronunciations without using non-native data is described and combined with the previous techniques to produce a robust adaptation to non-native accents in an automatic speech recognition system.".
- catalog extent "xi, 144 p. :".
- catalog identifier "3540003258 (softcover : alk. paper)".
- catalog isPartOf "Lecture notes in computer science ; 2560. Lecture notes in artificial intelligence".
- catalog isPartOf "Lecture notes in computer science ; 2560.".
- catalog isPartOf "Lecture notes in computer science. Lecture notes in artificial intelligence.".
- catalog issued "2002".
- catalog issued "c2002.".
- catalog language "eng".
- catalog publisher "Berlin ; New York : Springer,".
- catalog subject "006.4/54 21".
- catalog subject "Artificial intelligence.".
- catalog subject "Automatic speech recognition.".
- catalog subject "Computer science.".
- catalog subject "Languages, Modern Pronunciation by foreign speakers.".
- catalog subject "Natural language processing (Computer science)".
- catalog subject "TK7882.S65 G68 2002".
- catalog tableOfContents "ASR:AnOverview -- Pre-processing of the Speech Data -- Stochastic Modelling of Speech -- Knowledge Bases of an ASR System -- Speaker Adaptation -- Confidence Measures -- Pronunciation Adaptation -- Future Work -- Summary -- Databases and Experimental Settings -- MLLR Results -- Phoneme Inventory.".
- catalog title "Robust adaptation to non-native accents in automatic speech recognition / Silke Goronzy.".
- catalog type "text".