Speech recognition chip for monosyllables

Abstract-- In the paper, we present a real-time speech recognition chip for monosyllables such as A, B, ..., etc. The chip recognizes up to 64 monosyllables based on the Hidden Markov Model (HMM), which is a well known speaker-independent recognition method. The chip accepts a short-speech frame including 256 16

• Type: Conference
• Year: 2001
• Where: ASPDAC
• Authors: Kazuhiro Nakamura, Qiang Zhu, Shinji Maruoka, Takashi Horiyama, Shinji Kimura, Katsumasa Watanabe
• Keywords: ASPDAC 2001, Hardware, Hidden Markov Model, Speaker-independent Recognition Method, Speech Recognition Chip