Voice recognition system used in telephone apparatus
First Claim
1. Telephone apparatus with a voice recognition system, comprising a voice recognition unit and a separate input unit, wherein the separate input unit is provided at a prescribed distance from the voice recognition unit, the separate input unit including:
- a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance;
a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance, and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle;
a balance line for transmitting the audio signal generated by the hands-free microphone or the handset microphone; and
the voice recognition unit including an unbalance line, and comprising;
balance/unbalance converting means, connected to the balance line, for causing the audio signal transmitted by the balance line to be transmitted by the unbalance line;
high-pass filter means, connected to the unbalance line, for eliminating low frequency components from the signal transmitted by the unbalance line and for outputting a high-pass signal;
signal level control means for adjusting the level of the high-pass signal from the high-pass filter means in response to the on-hook signal or the off-hook signal and for outputting a speech data signal corresponding to a user'"'"'s utterance, the signal level control means causing the high-pass signal to have a first level when the hook switch generates the on-hook signal and a second level when the hook switch generates the off-hook signal;
storing means, coupled to the signal level control means, for storing speech data corresponding to the speech data signal from the signal level control means; and
control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least;
(a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance y a user is stored into the storing means; and
(b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data.
0 Assignments
0 Petitions
Accused Products
Abstract
A voice recognition system comprises a handset and a hands-free microphone for generating an input audio signal, a high-pass filter for eliminating low frequency components from the signal from the handset or hands-free microphone, a signal level controller for adjusting the level of the high-pass signal in response to the user of either the handset or hands-free microphone, a storer for storing the speech data and a controller for controlling the storer so that a user'"'"'s utterance is stored or the user'"'"'s utterance is recognized by comparing the utterance to speech data already stored. The handset hook switch provides an on-hook control signal to reduce amplifier gain during hands-free microphone operation.
88 Citations
35 Claims
-
1. Telephone apparatus with a voice recognition system, comprising a voice recognition unit and a separate input unit, wherein the separate input unit is provided at a prescribed distance from the voice recognition unit, the separate input unit including:
-
a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance; a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance, and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; a balance line for transmitting the audio signal generated by the hands-free microphone or the handset microphone; and the voice recognition unit including an unbalance line, and comprising; balance/unbalance converting means, connected to the balance line, for causing the audio signal transmitted by the balance line to be transmitted by the unbalance line; high-pass filter means, connected to the unbalance line, for eliminating low frequency components from the signal transmitted by the unbalance line and for outputting a high-pass signal; signal level control means for adjusting the level of the high-pass signal from the high-pass filter means in response to the on-hook signal or the off-hook signal and for outputting a speech data signal corresponding to a user'"'"'s utterance, the signal level control means causing the high-pass signal to have a first level when the hook switch generates the on-hook signal and a second level when the hook switch generates the off-hook signal; storing means, coupled to the signal level control means, for storing speech data corresponding to the speech data signal from the signal level control means; and control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least; (a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance y a user is stored into the storing means; and (b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data.
-
-
2. Telephone apparatus with a voice recognition system for recognizing input sounds uttered by an operator, comprising:
-
a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance; a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance, and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; high-pass filter means for eliminating low frequency components for the audio signal from the handset microphone or the hands-free microphone and outputting a high-pass signal; signal level control means for adjusting the level of the high-pass signal from the high-pass filter means in response to the on-hook signal or the off-hook signal and for outputting a speech data signal corresponding to a user'"'"'s utterance, the signal level control means causing the high-pass signal to have a first level when the hook switch generates the on-hook signal and a second level when the hook switch generates the off-hook signal; storing means, coupled to the signal level control means, for storing speech data corresponding to the speech data signal from the signal level control means; and control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least; (a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance by a user is stored into the storing means; and (b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data. - View Dependent Claims (3, 4)
-
-
5. Telephone apparatus with a voice recognition system for recognizing input sounds uttered by a user, comprising:
-
a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance; a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance, and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; high-pass filter means for eliminating low frequency components from the signal from the handset microphone or the hands-free microphone and outputting a high-pass signal; amplifying means, coupled to the high-pass filter means, for amplifying the high-pass signal from the high-pass filter means by an amplification factor selected from a plurality of amplification factors; selecting means, coupled to the amplifying means, for selecting the amplification factor in response to the on-hook signal or the off-hook signal, the selecting means causing the amplifying means to amplify the high-pass signal by a first one of the amplification factors in response to the on-hook signal and by a second one of the amplification factors in response to the off-hook signal; storing means, coupled to the output of the amplifying means, for storing speech data corresponding to the signal from the signal level control means; and control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least; (a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance by a user is stored into the storing means; and (b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data. - View Dependent Claims (6)
-
-
7. Telephone apparatus with a voice recognition system for recognizing input sounds uttered by an operator, comprising:
-
a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance; a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; high-pass filter means for eliminating low frequency components from the signal from the handset microphone or the hands-free microphone and outputting a high-pass signal; amplifying means, coupled to the high-pass filter means, for amplifying the high-pass signal from the high-pass filter means by an amplification factor selected from a plurality of amplification factors; adjusting means, coupled to an output and input of the amplifyign means, for adjusting an input level of the amplifying means so that an output level of the amplifying means is maintained within a prescribed range of magnitude; selecting means, coupled to the amplifying means, for selecting the amplification factor in response to the on-hook signal or the off-hook signal, the selecting means causing the amplifying means to amplify the high-pass signal by a first one of the amplification factors in response to the on-hook signal and by a second one of the amplification factors in response to the off-hook signal; storing means, coupled to the output of the amplifying means, for storing speech data corresponding to the signal from the amplifying means; and control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least; (a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance by a user is stored into the storing means; and (b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data.
-
-
8. Telephone apparatus with a voice recognition system for recognizing input sounds uttered by an operator, comprising:
-
a handset having a handset microphone for generating an audio signal representing a user'"'"'s utterance; a cradle having a hands-free microphone for generating an audio signal representing a user'"'"'s utterance and a hook switch for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; high-pass filter means for eliminating low frequency components from the signal from the handset microphone or the hands-free microphone and outputting a high-pass signal; amplifying means, coupled to the high-pass filter means, for amplifying the high-pass signal from the high-pass filter means by an amplification factor selected from a plurality of amplification factors in response to the on-hook signal or the off-hook signal, the amplifying means amplifying the high-pass signal by a first one of the amplification factors in response to the on-hook signal and by a second one of the amplification factors in response to the off-hook signal; adjusting means, coupled to an output and input of the amplifying means, for adjusting an input level of the amplifying means so that an output level of the amplifying means is maintained within a prescribed range of magnitude; storing means, coupled to the output of the amplifying means, for storing speech data corresponding to the signal from the amplifying means; and control means, coupled to the storing means, for controlling the storing means in one of a plurality of operational modes, the modes including at least; (a) a registration mode in which the control means controls the storing means so that speech data corresponding in a first utterance by a user is stored into the storing means; and (b) a voice recognition mode in which, in response to a second utterance by a user, the control means controls the storing means so as to retrieve speech data which is identical to speech data corresponding to the second utterance by comparing speech data corresponding to the second utterance with the speech data stored in the storing means and, in the event that speech data identical to the speech data corresponding to the second utterance is retrieved from the storing means, provides a recognition result corresponding to the identical speech data.
-
-
9. Telephone apparatus having a cradle, a handset and a voice recognition function, comprising:
-
a hands-free microphone connected to the cradle; a handset microphone provided in the handset; a hook-switch provided in the cradle for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; amplifier means, selectively connected to one of the hands-free microphone and the handset microphone, for amplifying signals applied from the microphone connected to the amplifier means by an amplification factor to set an amplitude level, the amplifier means amplifying the signals from the microphone connected to the amplifier means by a first amplification factor in response to the on-hook signal and by a second amplification factor in response to the off-hook signal; and recognition means, coupled to the output of the amplifier means, for recognizing signals amplified by the amplifier means. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. Telephone apparatus activated by a user'"'"'s utterance and providing hands-free operation for the user, comprising:
-
a hands-free microphone for generating an audio signal representing a user'"'"'s utterance; a handset microphone for generating an audio signal representing a user'"'"'s utterance; recognition means selectively connected to one of the hands-free microphone and the handset microphone for recognizing the audio signal form the microphone connected to the recognition means; and level control means, provided between the microphones and the recognition means and selectively coupled to one of the handset microphone and the hands-free microphone, for controlling a level of an output signal output by the level control means so that the recognized audio signal is amplified less when the recognized audio signal is the audio signal from the hands-free microphone than when the recognized audio signal is the audio signal from the handset microphone. - View Dependent Claims (17, 18, 19, 20, 21)
-
-
22. Telephone apparatus having a voice recognition function, wherein the telephone apparatus is activated by a user'"'"'s utterance, comprising:
-
first microphone input means for generating an audio signal representing a user'"'"'s utterance, the first microphone input means being provided in a handset of the telephone apparatus; second microphone input means for generating an audio signal representing a user'"'"'s utterance, the second microphone input means being provided at a prescribed distance from the user; amplifier means, selectively coupled to one of the first microphone input means and the second microphone input means, for amplifying signals applied from the microphone input means, an amplification level in the amplifier means being set to a first magnitude when the first microphone input means is coupled to the amplifier means, an amplification level in the amplifier means being set to a second magnitude when the second microphone input means is coupled to the amplifier means, and the second magnitude being lower than the first magnitude; and recognition means, coupled to the output of the amplifier means, for recognizing audio signals amplified by the amplifier means. - View Dependent Claims (23, 24, 25, 26, 27)
-
-
28. Telephone apparatus having a voice recognition function, wherein the telephone apparatus is activated by a user'"'"'s utterance, comprising:
-
first microphone input means for generating an audio signal representing a user'"'"'s utterance, the first microphone input means being provided in a handset of the telephone apparatus; second microphone input means for generating an audio signal representing a user'"'"'s utterance, the second microphone input means being provided at a prescribed distance from the user; recognition means, selectively connected to one of the first microphone input means and the second microphone input means, for recognizing audio signal from the microphone input means connected to the recognition means; and level control means, provided between the first and second microphone input means and the recognition means, and selectively coupled to one of the first microphone input means and the second microphone input means, for controlling a level of a signal output by the level control means so that the recognized audio signal is amplified less when the recognized audio signal is the audio signal from the second microphone input means than when the recognized audio signal is the audio signal from the first microphone input means. - View Dependent Claims (29, 30, 31, 32, 33)
-
-
34. Telephone apparatus having a cradle, a handset and a voice recognition function, comprising:
-
a hands-free microphone connected to the cradle; a handset microphone provided in the handset; a hook-switch provided in the cradle for generating an on-hook signal when the handset is mounted in the cradle and for generating an off-hook signal when the handset is dismounted from the cradle; amplifier means, selectively connected to one of the hands-free microphone and the handset microphone, for amplifying signals applied from the microphone connected to the amplifier means by an amplification factor to set an amplitude level, the amplifier means amplifying the signals from the microphone connected to the amplifier means by a first amplification factor in response to the on-hook signal and by a second amplification factor in response to the off-hook signal; and recognition means, coupled to the output of the amplifier means, for recognizing signals amplified by the amplifier means. - View Dependent Claims (35)
-
Specification