Demisyllable-based HMM spotting for continuous speech recognition

• Published in: [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing pp. 709 - 712 vol.1
• Main Authors: Lleida, E., Marino, J.B., Nedeu, C., Salavedra, J.
• Format: Conference Proceeding Publication
• Language: English
• Published: IEEE 1991; Institute of Electrical and Electronics Engineers (IEEE)
• Subjects: Acoustic testing; Enginyeria de la telecomunicació; Hidden Markov models; Lattices; Loudspeakers; Markov processes; Natural languages; Signal processing; Signal processing algorithms; Speech recognition; Telecommunication; Telecomunicació; Viterbi algorithm; Vocabulary; Àrees temàtiques de la UPC
• ISBN: 9780780300033; 0780300033
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.1991.150438

The authors describe the acoustic processor of a Spanish continuous speech recognition system based on demisyllable units. The acoustic processor is based on a spotting algorithm which takes as input the unknown utterance, the HMM (hidden Markov model) of the reference demisyllables, and the lexical knowledge in terms of a finite state network. The spotting algorithm is a modified version of the one-step Viterbi algorithm with multiple hypotheses. The output of the system is a lattice of word hypotheses suitable to be parsed by a linguistic analyzer. The proposed acoustic processor was tested using the integers from 0 to 1000 and telephonic numbers in a speaker-independent approach. The results show the good performance of the demisyllable as a recognition unit for the Spanish language and the efficiency of the spotting algorithm.< >