Articulation Rate Recognition by Using Artificial Neural Networks
This works concerns the problem of the application of artificial neural networks in the modelling of the hearing process. The aim of the research was to answer the question whether artificial neural networks are able to evaluate speech rate. Speech samples, first recorded during reading of a story with normal and next with slow articulation rate were used as research material. The experiment proceeded in two phases. In the first stage Kohonen network was used. The purpose of that network was to reduce the dimensions of the vector describing the input signals and to obtain the amplitude-time relationship. As a result of the analysis, an output matrix consisting of the neurons winning in a particular time frame was received. The matrix was taken as input for the following networks in the second phase of the experiment. Various types of artificial neural networks were examined with respect to their ability to classify correctly utterances with different speech rates into two groups. Good examination results were accomplished and classification correctness exceeded 88%.
KeywordsSpeech Signal Radial Basis Function Neural Network Automatic Speech Recognition Speech Rate Speaker Recognition
Unable to display preview. Download preview PDF.
- 1.Koopmans-vanBeinum FJ, vanDonzel ME (1996) Relationship between discourse structure and dynamic speech rate. In: Bunnell HT, Idsardi W (Eds), Proceedings ICSLP96, Vol 3, 1724–1727Google Scholar
- 2.Zheng J, Franco H, Stolcke A (2000) Rate-dependent acoustic modeling for large vocabulary conversational speech recognition. In: Proceeding ISCA Tutorial and Research Workshop on Automatic Speech Recognition: Challenges for the new Millennium, Paris, France, 145–149Google Scholar
- 4.Verhasselt JP Martens JP (1996) A fast and reliable rate of speech detector, Proceedings ICSLP96, Vol 3, 2258–2261Google Scholar
- 5.Guitar B, Kopff-Schaefer H, Donahu-Kilburg G, Bond L (1992) Parent verbal interactions and speech rate: A case study in stuttering. Journal of Speech and Hearing Research 35, 742–754Google Scholar
- 6.Howell P, Sackin S (2000) Speech rate modification and its effects on fluency reversal in fluent speakers and people who stutter. Journal of Developmental and Physical Disabilities 12(4)Google Scholar
- 9.Kohonen T (2001) Self-Organizing Maps. Springer, Berlin, Heidelberg, New YorkGoogle Scholar
- 10.Kestler HA, Schwenker F (2000) Classification of high-resolution ECG signals, In Howlett R, Jain L Radial basis function neural networks: theory and applications. Heidelberg: Physica-VerlagGoogle Scholar