Fundamentals of speech recognition
Fundamentals of speech recognition
Using Discriminant Eigenfeatures for Image Retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical language modeling for speech disfluencies
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Discriminative mixture weight estimation for large Gaussian mixture models
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Modeling filled pauses for spontaneous speech recognition applications
AEE'08 Proceedings of the 7th WSEAS International Conference on Application of Electrical Engineering
Slovenian spontaneous speech recognition and acoustic modeling of filled pauses and onomatopoeas
WSEAS Transactions on Signal Processing
Contextual maximum entropy model for edit disfluency detection of spontaneous speech
ISCSLP'06 Proceedings of the 5th international conference on Chinese Spoken Language Processing
Hi-index | 0.00 |
Most automatic speech recognizers (ASRs) concentrate on read speech, which is different from spontaneous speech with disfluencies. ASRs cannot deal with speech with a high rate of disfluencies such as filled pauses, repetitions, lengthening, repairs, false starts and silence pauses. In this paper, we focus on the feature analysis and modeling of the filled pauses “ah,” “ung,” “um,” “em,” and “hem” in spontaneous speech. Karhunen-Loéve transform (KLT) and linear discriminant analysis (LDA) were adopted to select discriminant features for filled pause detection. In order to suitably determine the number of discriminant features, Bartlett hypothesis testing was adopted. Twenty-six features were selected using Bartlett hypothesis testing. Gaussian mixture models (GMMs), trained with a gradient decent algorithm, were used to improve the filled pause detection performance. The experimental results show that the filled pause detection rates using KLT and LDA were 84.4% and 86.8%, respectively. A significant improvement was obtained in the filled pause detection rate using the discriminative GMM with KLT and LDA. In addition, the LDA features outperformed the KLT features in the detection of filled pauses.