Speech recognition using polynomial expansion and hidden markov models

A speech recognition system having a sampler block and a feature extractor block for extracting time domain and spectral domain parameters from a spoken input speech into a feature vector. A polynomial expansion block generates polynomial coefficients from the feature vector. A correlator block, a s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Barron, David L, Yip, William Chunhung
Format: Patent
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A speech recognition system having a sampler block and a feature extractor block for extracting time domain and spectral domain parameters from a spoken input speech into a feature vector. A polynomial expansion block generates polynomial coefficients from the feature vector. A correlator block, a sequence vector block, an HMM table and a Viterbi block perform the actual speech recognition based on the speech units stored in a speech unit table and the HMM word models stored in the HMM table. The HMM word model that produces the highest probability is determined to be the word that was spoken.