Speech Sound Detection Apparatus Frequency Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech sound detection apparatuses face challenges in accurately determining whether input sound is speech sound due to variations in microphone characteristics and signal transmission, leading to inconsistent power levels across multiple microphones, which complicates precise sound classification.
Innovation Solution
A speech sound detection apparatus that includes a sound reception unit, input power computation unit, correction function estimation unit, input power correcting unit, and speech sound detection unit, which computes input power at every frequency, estimates a continuous correction function to approximate input power to a reference power, and corrects the input power using a correction coefficient, enabling precise determination of speech sound.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a signal correction device is applied to correct input power of audio signals from multiple microphones, then measurement precision of speech sound detection is improved, but device complexity increases due to additional correction processing
Solution Approach 1:
The patent applies parameter changes by computing correction coefficients based on frequency characteristics and applying these coefficients to normalize input power across different microphones. The correction function estimates frequency-dependent parameters (correction coefficients) that transform the input power distribution to match reference power levels, thereby resolving the contradiction between measurement precision and device complexity through mathematical parameter adjustment rather than hardware modification
2Measurement precision
If correction coefficient is determined for excessively high or low frequency audio signals, then correction accuracy deteriorates due to noise and delay, but attempting to correct all frequencies increases device complexity
Solution Approach 1:
The patent applies local quality by determining whether to compute correction coefficients based on the frequency characteristics of the input audio signal. For frequencies outside the speech sound range (excessively high or low frequencies), the system identifies these as local regions with harmful characteristics and skips correction coefficient computation in those specific frequency regions, thereby improving correction accuracy by avoiding noise and delay impacts while maintaining simple device operation
Solution Approach 2:
The patent applies partial action by selectively computing correction coefficients only for frequency ranges that contain speech sound signals, rather than attempting to correct all frequencies. This partial correction approach avoids the harmful effects of noise and delay in excessive frequency regions while maintaining adequate correction for the relevant speech frequency range, resolving the contradiction between correction accuracy and harmful factors
Data Source
AI summary
A speech sound detection apparatus receives an input audio signal (as a sound reception unit), and computes input power that indicates a magnitude of the sound represented by the audio signal (as an input power computation unit). The apparatus estimates a correction function that is a continuous function defining a relation between a certain frequency and a correction coefficient used to approximate the input power computed at that frequency to the reference power predetermined for that frequency (as a correction function estimation unit). The apparatus corrects the input power at every frequency, based upon the correction coefficient that is obtained in accordance with the relation defined by the estimated correction function (as an input power correcting unit). The apparatus further determines whether or not the sound represented by the received audio signal is speech sound, based upon the corrected input power (as a speech sound detection unit).