Unsupervised adaptation of a large vocabulary automatic speech recognizer
Номер патента: EP1097446A1
Опубликовано: 09-05-2001
Автор(ы): Gary N. Tajchman, Heiko W. Rahmel, Ian S. Boardman, Roger S. Zimmerman, Thomas B. Schalk
Принадлежит: KONINKLIJKE PHILIPS ELECTRONICS NV
Опубликовано: 09-05-2001
Автор(ы): Gary N. Tajchman, Heiko W. Rahmel, Ian S. Boardman, Roger S. Zimmerman, Thomas B. Schalk
Принадлежит: KONINKLIJKE PHILIPS ELECTRONICS NV
Реферат: A method of improving the recognition accuracy of a speech recognizer deployed in an environment to receive live input data. Live input data and associated recognition responses are collected and then used as inputs to a given speaker independent adaptation algorithm. The algorithm is then used to enhance the accuracy of the speech recognizer without human supervision. This technique is useful for adapting a large vocabulary ASR engine.
Unsupervised adaptation of a large vocabulary automatic speech recognizer
Номер патента: WO2000070603A1. Автор: Thomas B. Schalk,Roger S. Zimmerman,Gary N. Tajchman,Ian S. Boardman,Heiko W. Rahmel. Владелец: KONINKLIJKE PHILIPS ELECTRONICS N.V.. Дата публикации: 2000-11-23.