Patent
Method of rejection of unknown words in isolated words speech recognition
TLDR
In this article, a sound signal processing method involves evaluating the signal distribution value (VM), the word duration value (WM), the similarity value (AM) and the difference value (DM) of the sound signals via a fuzzy technique.Abstract:
The sound signal processing method involves evaluating the signal distribution value (VM), the word duration value (WM), the similarity value (AM) and the difference value (DM) of the sound signals via a fuzzy technique. This provides a probability value indicating the likelihood that the sound signals contain a given word. The input lines (10,1214,16) can be coupled in pairs to a noise filter (18) and to a word filter (20), with both filters coupled to a combining stage (28) and with a fuzzy output device (36) coupled to an output stage (40).read more
References
More filters
Patent
A method and apparatus for speech detection
TL;DR: In this paper, a speech detection apparatus consisting of a reference model maker for extracting a plurality of parameters for speech detection from training data, and a model based on the parameters; a parameter extractor for extracting the plurality of parameter from each frame of an input audio signal; and a decision device for deciding whether the audio signal is speech or not, by comparing the parameters extracted from the input signal with the reference model.
Proceedings ArticleDOI
A fuzzy acoustic-phonetic decoder for speech recognition
TL;DR: A general framework for acoustic-phonetic modelling is developed and context-sensitive rules are incorporated into a knowledge-based automatic speech recognition (ASR) system and are assessed with control based on fuzzy decision-making.