Recognition of speech or speech-like sounds

• US 4,516,215 A
• Filed: 09/09/1982
• Issued: 05/07/1985
• Est. Priority Date: 09/11/1981
• Status: Expired due to Term

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Hakaridani, Mitsuhiro, Iwahashi, Hiroyuki, Nishioka, Yoshiki
• Primary Examiner(s): KEMENY, EMANUEL
• Application Number:
  US06/416,165
• Time in Patent Office: 971 Days
• Field of Search: 381/41-43, 381/110, 367/198, 364/513.5
• US Class Current: 704/234
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence

Abstract

Speech recognition using self-correlation (auto-correlation) parameters and time normalization is improved by first making a preliminary decision using lower-order (zeroth to third) self-correlation coefficients derived from the self-correlation function of order m: ##EQU1## where φ(0) is the power, φ(1) is the linear or first order coefficient, and so on.

Claims

1. A method of speech recognition comprising the steps of creating self-correlation functions for input sound signals, deciding the intervals of the sound signals, normalizing the time axes in conjunction with the sound intervals, and conducting recognition of words or the like through decisions using said self-correlation functions as feature parameters where there is matching with reference patterns,

said method further comprising the step of effecting preliminary selection prior to the final recognition step by means of linear matching using said self-correlation functions of lower degrees.