PatentDOI
Speech recognition apparatus
TLDR
In this paper, a speech recognition apparatus for raising the recognition speed, which is provided with first and second processors, is described, where the first processor mainly carries out feature extraction of the input speech, and the second one mainly carrying out comparison and distinction of feature extraction patterns with and from the reference patterns.Abstract:
This invention relates to a speech recognition apparatus for raising the recognition speed, which is provided with first and second processors, the first processor mainly carrying out feature extraction of the input speech, the second one mainly carrying out comparison and distinction of feature extraction patterns with and from the reference patterns, thereby processing the feature extraction hand comparison and distinction in an equilibrium manner and expecting the speech recognition at high speed. Another apparatus has been proposed which allows the first processor to carry out the comparison and distinction process in parts, thereby raising the recognition rate and performing the recognition at further high speed.read more
Citations
More filters
Patent
Method and apparatus for automatically recognizing input audio and/or video streams
Stephen C. Kenyon,Laura Simkins +1 more
TL;DR: In this paper, a method and system for the automatic identification of audio, video, multimedia, and/or data recordings based on immutable characteristics of these works is presented, where each work to be recognized is "played" into the system where it is subjected to an automatic signal analysis process that locates salient features and computes a statistical representation of these properties.
Patent
Speech recognition using multiple recognizers (selectively) applied to the same input sample
TL;DR: In this article, a speech sample is recognized with a computer system by processing the speech sample with at least two speech recognizers, each of which has a different performance characteristic, such as style or subject matter.
Patent
Speech recognition using preclassification and spectral normalization
TL;DR: In this article, a two-stage classification process is used in a speech recognition system, in which a slope vector template is generated from an extended LPC analysis using a universal bandwidth expansion technique.
Patent
Signal adaptive processor
TL;DR: In this paper, a signal adaptive processor for detecting and identifying specific sound signals that are emitted by relatively moving or at rest sources in noisy environments is presented, which can provide an early warning system to alert vehicle operators of the presence of emergency vehicles which emit audio warning signals.
Patent
Audiovisual synchronization signal generator using audio signature comparison
TL;DR: In this paper, a method and apparatus for synchronizing a plurality of signals to a desired signal is presented, which provides real time synchronization of similar audio and any associated sequence of images, either on video or on film, without the need for a separate reference or carrier frequency to be added to both signals.
References
More filters
Journal ArticleDOI
Dynamic programming algorithm optimization for spoken word recognition
TL;DR: This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition, in which the warping function slope is restricted so as to improve discrimination between words in different categories.
PatentDOI
Speech recognition system
Sadakazu Watanabe,Hidenori Shinoda,Tsuneo Nitta,Yoichi Takebayashi,Shouichi Hirai,Tomio Sakata,Kensuke Uehara,Yasuo Takahashi,Haruo Asada +8 more
TL;DR: A speech recognition system prompts a user to provide a first utterance, which is recorded, processed and compared to the second utterance to detect at least one acoustic difference.
PatentDOI
Device for recognizing an input pattern with approximate patterns used for reference patterns on mapping
TL;DR: In a speech recognition system which time-normalizes each pre-stored reference pattern of feature vectors bj before comparison with the input signal pattern vectors ai, an improved time-alignment technique requiring less calculation is implemented by selecting "standard" vectors vm(j) which approximate the reference vectors thereby simplifying the derivation of the time-warp mapping function j=j(i).
PatentDOI
Speech recognition system
TL;DR: In this article, an element vector of a speech is classified to the first portion and the second portion, where the former is a consonant and co-articulation which couples the two sounds, and the latter is a vowel.
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.