H
Hiroyuki Iwahashi
Researcher at National Archives and Records Administration
Publications - 20
Citations - 162
Hiroyuki Iwahashi is an academic researcher from National Archives and Records Administration. The author has contributed to research in topics: Syllable & Feature (machine learning). The author has an hindex of 9, co-authored 20 publications receiving 162 citations.
Papers
More filters
PatentDOI
Speech recognition system
TL;DR: In this article, a voice recognition system which can recognize the voice of a specific speaker, which has previously been analyzed, distinctive features extracted, and the pattern of those distinctive features registered, is arranged so that, preferably at the time of registration of the distinctive features pattern, based on the detection of a voice interval, the voice data is entered into temporary storage.
PatentDOI
Recognition of speech or speech-like sounds
TL;DR: In this article, an improved method of speech recognition suitable for use in simple type speech recognition systems is disclosed, which uses short time self-correlation functions as feature parameters for recognition of speech or speech-like words and especially effecting preliminary selection utilizing part of data for final recognition.
PatentDOI
Method of speech recognition
TL;DR: In a speech recognition system, similarity calculations between speech feature patterns are reduced by stopping similarity calculations for any one reference pattern when a frame in the pattern fails to exceed a corresponding similarity threshold as discussed by the authors.
PatentDOI
Speech recognition with preliminary matching
TL;DR: In this article, the final matching operation for each characteristic pattern is executed according to the preliminarily selected order prior to final matching, where any further calculation in reference to such a pattern is not executed after a specific condition has been satisfied during the matching calculation, and as result, calculation requirements can be drastically minimized.
PatentDOI
Voice recognition method and apparatus by updating reference patterns
TL;DR: In this article, each syllable is compared with standard syllables preregistered in a memory and thereby recognized but corrections may be made on erroneous recognitions by referencing a dictionary or entering a command.