Apparatus and method for correcting a speech signal for ambient noise in a vehicle
First Claim
1. A speech correction apparatus comprising:
- a speaker for generating speech to be corrected;
a microphone set at a hearing position;
a signal separating unit for separating ambient noise from the speech to be corrected at the hearing position;
a speech correcting unit for correcting a sound pressure level of the speech to be corrected generated by the speaker based on an average power of the speech to be corrected and an average power of the ambient noise, which are separated by the signal separating unit; and
a speech-head correcting unit for correcting an average power of a speech-head at the border between a silent state and a speech state in the speech to be corrected, wherein the average power of the speech-head is corrected based on a comparison between a time length Ls for calculating the average power of the speech to be corrected and a time length Ln for calculating the average power of the ambient noise.
1 Assignment
0 Petitions
Accused Products
Abstract
A speech correction apparatus includes a speaker for generating guidance speech; a microphone set at a hearing position; an acoustic-characteristic setting unit for separating ambient noise from the guidance speech at the hearing position; an operating unit; a speech correcting filter for correcting the sound pressure level of the guidance speech generated by the speaker based on the average power of the guidance speech and the average power of the ambient noise which are separated; a loudness-compensating-gain calculating unit; and a speech-head correcting unit for correcting the average power of the guidance speech corresponding to the speech head at the border between a silent state and a speech state of the guidance speech.
-
Citations
26 Claims
-
1. A speech correction apparatus comprising:
-
a speaker for generating speech to be corrected; a microphone set at a hearing position; a signal separating unit for separating ambient noise from the speech to be corrected at the hearing position; a speech correcting unit for correcting a sound pressure level of the speech to be corrected generated by the speaker based on an average power of the speech to be corrected and an average power of the ambient noise, which are separated by the signal separating unit; and a speech-head correcting unit for correcting an average power of a speech-head at the border between a silent state and a speech state in the speech to be corrected, wherein the average power of the speech-head is corrected based on a comparison between a time length Ls for calculating the average power of the speech to be corrected and a time length Ln for calculating the average power of the ambient noise. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A speech correction apparatus comprising:
-
a speaker for generating speech to be corrected; a microphone set at a hearing position; a signal separating unit for separating ambient noise from the speech to be corrected at the hearing position; a speech correcting unit for correcting a sound pressure level of the speech to be corrected generated by from the speaker based on an average power of the speech to be corrected and an average power of the ambient noise, which are separated by the signal separating unit; and a speech-head correcting unit for stopping correction of the sound pressure level which is performed by the speech correcting unit in accordance with a speech-head at the border between a silent state and a speech state in the speech to be corrected, wherein the correction of the sound pressure level is stopped based on a comparison between a time length Ls for calculating the average power of the speech to be corrected and a time length Ln for calculating the average power of the ambient noise. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A speech correction apparatus comprising:
-
a speaker for generating speech to be corrected; a microphone set at a hearing position; a signal separating unit comprising; a filter having an acoustic characteristic as an impulse response of an acoustic system between the speaker and the microphone; and an operating unit for subtracting a signal which is obtained by passing a signal supplied to the speaker according to the speech to be corrected through the filter from a signal received from the microphone when the speech to be corrected is generated by the speaker, wherein a signal corresponding to the speech to be corrected is supplied by the filter and a signal corresponding to the ambient noise is supplied from the operating unit, so that the ambient noise is separated from the speech to be corrected at the hearing position; a coefficient update unit for updating a filter coefficient of the filter so that the power of the signal supplied from the operating unit is minimized; a filter initial setting unit for setting an initial value of the filter coefficient, which is updated by the coefficient update unit, at a value other than 0; and a speech correcting unit for correcting a sound pressure level of the speech to be corrected generated by the speaker based on a comparison between a time length Ls for calculating an average power of the speech to be corrected and a time length Ln for calculating an average power of the ambient noise, which are separated by the signal separating unit. - View Dependent Claims (17, 18, 19, 20, 21)
-
-
22. A speech correcting method for a speech correction apparatus comprising:
-
a speaker for generating speech to be corrected; a microphone set at a hearing position; a filter having an acoustic characteristic as an impulse response of an acoustic system between the speaker and the microphone; and an operating unit for subtracting a signal which is obtained by passing a signal supplied to the speaker according to the speech to be corrected through the filter from a signal received from the microphone when the speech to be corrected is generated by the speaker, the speech correcting method comprising; an act of separating, by a signal separating unit, the ambient noise from the speech to be corrected at the hearing position by supplying a signal corresponding to the speech to be corrected from the filter and supplying a signal corresponding to the ambient noise from the operating unit; an act of updating, by a coefficient update unit, a filter coefficient of the filter so as to minimize the power of the signal supplied from the operating unit; an act of setting an initial value of the filter coefficient, which is updated by the coefficient update unit, at a value other than 0 by a filter initial setting unit; and an act of correcting a sound pressure level of the speech to be corrected generated by the speaker based on a comparison between a time length Ls for calculating an average power of the speech to be corrected and a time length Ln for calculating an average power of the ambient noise, which are separated by the signal separating unit, the correction being performed by a speech correcting unit. - View Dependent Claims (23, 24, 25, 26)
-
Specification