RECOGNITION SYSTEM WITH GENERATION OF FEATURE PARAMETERS

Patent №

US 4,833,711

Granted

1989-05-23

Filed 1983

Owner

COMPUTER BASIC TECHNOLOGY RESEARCH ASSOCIATION, 4-28 MITA 1-CHOME, MINATO-KU, TOKYO, JAPAN

+1 more

Lab

—

AI components

ml · speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

06543497

View graph

In a speech recognition system, logarithmic amplifiers avoid low level signal or noise problems by clamping all signals below an input threshold to a constant output level.

Machine learning SpeechG10L 15/20G10L 15/00

Google Patents

AI classification

Speech1.00

Machine learning0.55

Evolutionary computation0.11

AI hardware0.03

Vision0.02

Natural language0.01

Planning0.00

Knowledge representation0.00

Ownership

COMPUTER BASIC TECHNOLOGY RESEARCH ASSOCIATION, 4-28 MITA 1-CHOME, MINATO-KU, TOKYO, JAPAN

assignment · 41880133

SHARP KABUSHIKI KAISHA

assignment · 59030244

Assignors

UEDA, TORU, NISHIOKA, YOSHIKI

On an employer assignment, the assignors are typically the inventors.

Cites (9)

METHOD AND APPARATUS FOR USE IN PROCESSING SIGNALSUS 4,591,928 · 1986 SPEECH RECOGNITION SYSTEMUS 4,520,500 · 1985 METHOD AND APPARATUS FOR SPEECH MESSAGE RECOGNITIONUS 4,509,186 · 1985 ENDPOINT DETECTORUS 4,370,521 · 1983 DEVICE FOR RECOGNIZING AN INPUT PATTERN WITH APPROXIMATE PATTERNS USED FOR REFERENCE PATTERNS ON MAPPINGUS 4,256,924 · 1981 DIGITAL VOCODERUS 3,975,587 · 1976 Patent US 4,008,375US 4,008,375 Patent US 4,158,750US 4,158,750 Patent US 4,243,837US 4,243,837

Cited by (2)

NOISE RESISTANT AUDITORY MODEL FOR PARAMETRIZATION OF SPEECHUS 5,537,647 · 1996 Patent US 5,216,748US 5,216,748

Related research

An isolated word recognition system based on hidden Markov-logarithmic adjustment method is implemented to solve the decimal overflow problemOpenAlex Speech Recognition Front End Without Information LossarXiv Analysis of Amplitude Threshold on Speech Recognition SystemSemantic Scholar Robust speaker recognition based on biologically inspired featuresSemantic Scholar Improved Feature Parameter Extraction from Speech Signals Using Machine Learning AlgorithmSemantic Scholar

Full text

Google Patents