Vocabulary independent speech recognition using particles
Tóm tắt
A method is presented for performing speech recognition that is not dependent on a fixed word vocabulary. Particles are used as the recognition units in a speech recognition system which permits word-vocabulary independent speech decoding. A particle represents a concatenated phone sequence. Each string of particles that represents a word in the one-best hypothesis from the particle speech recognizer is expanded into a list of phonetically similar word candidates using a phone confusion matrix. The resulting word graph is then re-decoded using a word language model to produce the final word hypothesis. Preliminary results on the DARPA HUB4 97 and 98 evaluation sets using word bigram redecoding of the particle hypothesis show a WER of between 2.2% and 2.9% higher than using a word bigram speech recognizer of comparable complexity. The method has potential applications in spoken document retrieval for recovering out-of-vocabulary words and also in client-server based speech recognition.
Từ khóa
#Vocabulary #Speech recognition #Decoding #Indexing #Concatenated codes #Automatic speech recognition #Laboratories #Speech analysis #Linear approximation #Natural languagesTài liệu tham khảo
whittaker, 2000, Particle-based Language Modelling, Proceedings of the International Conference on Spoken Language Processing
wang, 2001, Multi-scale Audio Indexing for Translingual Spoken Document Re-trieval, Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing
jelinek, 1997, Statistical Methods for Speech Recognition
whittaker, 2000, Statistical Language Modelling for Automatic Speech Recognition of Russian and English
pusateri, 2001, N-Best List Generation using Word and Phoneme Recognition Fusion, Proceedings of the European Conference on Speech Communication and Technology
coletti, 1999, A two-stage speech recognition method for information retrieval applications, Proceedings of the European Conference on Speech Communication and Technology
10.1109/ICASSP.2000.859326
10.1145/133160.133194