Speech Analysis Based on a Model of the Auditory System.

reportActive / Technical Report | Accession Number: ADA167426 | Open PDF

Abstract:

This report describes a signal processing technique for speech signals based on a model of the processing done in the auditory system. It has been found that the click response of the auditory system is an exponential function. The spectrogram produced by a speech waveform that has been windowed by the same function possesses excellent resolution of both time and frequency parameters of the signal. It is expected that this analysis method will improve the discrimination of phonemic elements, and will prove useful in such applications as speech recognition and speech compression. Keywords Auditory modelling Speech perception Artificial intelligence.

Author(s):
Rhody, Harvey E. ; Houde, Robert A. ; Parkins, Charles W. ; Dianat, Sohiel
Author Organization(s):
ROCHESTER INST OF TECH NY DEPT OF ELECTRICAL ENGINEERING
Descriptive Note:
Final rept. Oct 83-Sep 85,
Pagination:
0054

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
RADC-TR-85-265
Contract/Grant Number(s):
F30602-81-C-0169
Task Number(s):
J8
Project Number(s):
2305
Monitor Series:
TR-85-265
 Subject Terms
Joint Capability Areas:
JCA_2_Battlespace Awareness; JCA_6.3.3_Spectrum Management; JCA_2.2.1_Signals Collection; JCA_2.2_Collection; JCA_6_Net Centric; JCA_5_Command and Control; JCA_2.4.5_Product Generation; JCA_2.4.2_Evaluation; JCA_2.4.3_Interpretation; JCA_6.3_Net Management; JCA_2.4_Analysis Prediction and Production; JCA_5.3_Planning; JCA_6.1_Information Transport; JCA_1_Force Support; JCA_8_Building Partnerships; JCA_8.2.5_Strengthen Global Defense Posture; JCA_8.2_Shape; JCA_1.2_Force Preparation; JCA_1.2.7_Experimentation; JCA_1.2.1_Training
Modernization Areas:
Fully Networked C3
Communities of Interest:
Materials and Manufacturing Processes
Descriptor(s):
*SPEECH ANALYSIS, SIGNAL PROCESSING, FREQUENCY, MODELS, PARAMETERS, PROCESSING, WAVEFORMS, SIGNALS, SPEECH RECOGNITION, SPEECH, DISCRIMINATION, EXPONENTIAL FUNCTIONS, HEARING, AUDITORY PERCEPTION, SPEECH COMPRESSION, PHONEMES
Field(s)/Group(s):
Acoustics
Keyword(s):
PE61102F, WURADC2305J8P9
Report Date:
1986 Feb 01