00000nam 2200000zi 4500 9.890766 CaOODSP 20221107172708 m o d f cr mn||||||||| 200821t19921992onca ob f000 0 eng d CaOODSP eng rda CaOODSP eng eng fre Co24-3/8-1992-1E-PDF Treurniet, W. C. (William C.) author. Neural network classifier architectures for phoneme recognition / by William Treurniet. Ottawa : Communications Research Centre, Broadcast Technologies Research = Centre de recherches sur les communications, Recherche en technologies de radiodiffusion, 1992. ©1992. 1 online resource (iii, 38 pages) : illustrations. text txt rdacontent computer c rdamedia online resource cr rdacarrier CRC technical note ; no. CRC-TN-92-001 "Ottawa, March 26, 1992." Digitized edition from print [produced by Innovation, Science and Economic Development Canada]. Includes bibliographical references (pages 36-38). "Automatic recognition of words in continuous speech is difficult to do with whole-word template models, especially when the vocabulary is reasonably large. Instead, the currently preferred approaches for this task hypothesize the presence of words or sub-words, such as syllables or phonemes, on the basis of likelihood estimates obtained from comparisons of the acoustic data with statistical models derived from training data. This paper is concerned with the application of artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base"--Abstract. Issued also in print format. Includes abstracts in English and French. Automatic speech recognition. Neural networks (Computer science) Reconnaissance automatique de la parole. Réseaux neuronaux (Informatique) Communications Research Centre (Canada), issuing body. CRC technical note ; no. 92-001. (CaOODSP)9.882494 PDF 1.46 MB https://publications.gc.ca/collections/collection_2020/isde-ised/Co24/Co24-3-8-1992-1-eng.pdf