Radiotelephone voice control device, in particular for use in a motor vehicle

• US 6,263,216 B1
• Filed: 10/04/1999
• Issued: 07/17/2001
• Est. Priority Date: 04/04/1997
• Status: Expired due to Term

• Current Assignee: Parrot Automotive
• Original Assignee: Parrot SA
• Inventors: Besnard, Nicolas, Seydoux, Henri
• Primary Examiner(s): Bost, Dwayne
• Assistant Examiner(s): Trinh, Sonny
• Application Number:
  US09/411,382
• Time in Patent Office: 652 Days
• Field of Search: 455/79, 455/563, 455/67.7, 455/414, 455/564, 704/241, 704/246, 704/248, 704/250, 704/333, 704/226, 704/227, 704/228, 704/275, 704/253, 379/88.01, 379/88.02, 379/88.03
• US Class Current: 455/564
• CPC Class Codes: G10L 15/12 using dynamic programming techniques, e.g. dynamic time warping [DTW]
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2021/02168 the estimation exclusively taking place during speech pauses
• CPC Class Codes: H01M 10/48 Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte constructional details of current conducting connections for detecting conditions inside cells or batteries, e.g. details of voltage sensing terminals, H01M50/569
• CPC Class Codes: H01M 2200/10 Temperature sensitive devices
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 1/6075 adapted for handsfree use in a vehicle H04M1/6058 takes precedence; arrangements for holding telephones in a vehicle B60R11/0241
• CPC Class Codes: Y02E 60/10 Energy storage using batteries

Abstract

The apparatus comprises a data memory containing a series of correspondents'"'"' call numbers and, for each call number, at least one associated voice print; a sound transducer suitable for picking up the name of a desired corespondent as spoken by the user of the apparatus; voice recognition means suitable for analyzing the correspondent'"'"'s name as picked up by the transducer and for transforming it into an associated voice print; selective memory addressing means including associative means suitable for finding a voice print in the memory corresponding to the print supplied by the voice recognition means, and in the event of a match, for addressing the corresponding memory position; and means co-operating with the associative means for applying the addressed call number to the radiotelephone circuits. The voice recognition means evaluate and store a current noise level as picked up by the transducer in the absence of a speech signal; when in the presence of a speech signal, they subtract the previously evaluated current noise level from the signal as picked up; and then they apply the resulting signal as obtained in this way to a DTW type voice recognition algorithm with pattern recognition by dynamic programming adapted to speech using dynamic parameter extraction functions, in particular a predictive dynamic algorithm with forward and/or backward and/or frequency masking.

Claims

1. Voice control apparatus for a radiotelephone, in particular for use in a motor vehicle, the apparatus comprising:

a data memory containing a series of correspondents'"'"' call numbers and, for each call number, at least one associated voice print;

a sound transducer suitable for picking up the name of a desired correspondent as uttered by the user of the apparatus;

voice recognition means suitable for analyzing the correspondent'"'"'s name as picked up by the transducer and for transforming it into an associated voice print;

selective memory addressing means including associative means suitable for finding a voice print in the memory corresponding to the print supplied by the voice recognition means, and in the event of a match, for addressing the corresponding memory position; and

means cooperating with the associative means for applying the addressed call number to the radiotelephone circuits;

the voice recognition means comprising;

means capable of evaluating and storing a current noise level as picked up by the transducer in the absence of a speech signal, said noise being picked up continuously by the sound transducer and analyzed to give a weighted mean energy spectrum of the noise, which spectrum is continuously updated;

means capable, in the presence of a speech signal, of subtracting the previously evaluated noise power spectrum from the power spectrum of the signal as picked up; and

means capable of applying the resulting signal as obtained in this way to a DTW type voice recognition algorithm with pattern recognition by dynamic programming adapted to speech using dynamic parameter extraction functions, in particular a predictive dynamic algorithm with forward and/or backward and/or frequency masking, further comprising a key actuated by the user and whose actuation controls radiotelephone control functions including answering, hanging up, and swapping during call waiting.

2. Voice control apparatus for a radiotelephone, in particular for use in a motor vehicle, the apparatus comprising:

a data memory containing a series of correspondents'"'"' call numbers and, for each call number, at least one associated voice print;

a sound transducer suitable for picking up the name of a desired correspondent as uttered by the user of the apparatus;

voice recognition means suitable for analyzing the correspondent'"'"'s name as picked up by the transducer and for transforming it into an associated voice print;

selective memory addressing means including associative means suitable for finding a voice print in the memory corresponding to the print supplied by the voice recognition means, and in the event of a match, for addressing the corresponding memory position; and

means cooperating with the associative means for applying the addressed call number to the radiotelephone circuits;

the voice recognition means comprising;

means capable of evaluating and storing a current noise level as picked up by the transducer in the absence of a speech signal, said noise being picked up continuously by the sound transducer and analyzed to give a weighted mean energy spectrum of the noise, which spectrum is continuously updated;

means capable, in the presence of a speech signal, of subtracting the previously evaluated noise power spectrum from the power spectrum of the signal as picked up; and

means capable of applying the resulting signal as obtained in this way to a DTW type voice recognition algorithm with pattern recognition by dynamic programming adapted to speech using dynamic parameter extraction functions, in particular a predictive dynamic algorithm with forward and/or backward and/or frequency masking, further comprising a key actuated by the user to mark a speech signal, and in which the signal picked up by the transducer is stored continuously over a given time interval (k₀) so as to perform voice recognition over a length of time ([T₀−

k₀, T₁+k₁]) including the period during which said key is actuated ([T₀, T₁]) plus said time interval (k₀) immediately preceding said actuation.

3. Voice control apparatus for a radiotelephone, in particular for use in a motor vehicle, the apparatus comprising:

a data memory containing a series of correspondents'"'"' call numbers and, for each call number, at least one associated voice print;

a sound transducer suitable for picking up the name of a desired correspondent as uttered by the user of the apparatus;

voice recognition means suitable for analyzing the correspondent'"'"'s name as picked up by the transducer and for transforming it into an associated voice print;

selective memory addressing means including associative means suitable for finding a voice print in the memory corresponding to the print supplied by the voice recognition means, and in the event of a match, for addressing the corresponding memory position; and

means cooperating with the associative means for applying the addressed call number to the radiotelephone circuits;

the voice recognition means comprising;

means capable of evaluating and storing a current noise level as picked up by the transducer in the absence of a speech signal, said noise being picked up continuously by the sound transducer and analyzed to give a weighted mean energy spectrum of the noise, which spectrum is continuously updated;

means capable, in the presence of a speech signal, of subtracting the previously evaluated noise power spectrum from the power spectrum of the signal as picked up; and

means capable of applying the resulting signal as obtained in this way to a DTW type voice recognition algorithm with pattern recognition by dynamic programming adapted to speech using dynamic parameter extraction functions, in particular a predictive dynamic algorithm with forward and/or backward and/or frequency masking, further comprising a key actuated by the user to mark a speech signal, and in which voice recognition is performed over a length of time ([T₀−

k₀, T₁+k₁]) terminating after the end (T₁) of actuation of the key.