公开(公告)号：DE3688614T2

公开(公告)日：1993-10-07

申请号：DE3688614

申请日：1986-12-18

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS ,  SMANSKI PHILIP JEROME

IPC: G10L11/00 ,  A61K35/14 ,  A61K38/00 ,  A61P31/12 ,  A61P35/00 ,  C07K1/20 ,  C07K14/395 ,  C07K14/52 ,  C07K14/54 ,  C12N15/09 ,  C12P21/02 ,  C12R1/865 ,  G10L15/06 ,  G10L15/10 ,  G10L15/18 ,  G10L5/00

Abstract: Described herein, is an arrangement and method for processing speech information in a speech recognition system (300). In such a system where the speech information is depicted as words, each word representing a sequence of frames (510) and where the recognition system has means (120) for comparing present input speech to a word template, the word template stored in template memory and derived from one or more previous input word, the present invention is best employed. The invention describes combining contiguous acoustically similar frames (512) derived from the previous input word or words into representative frames to form a corresponding reduced word template, storing the reduced word template in template memory in an efficient manner, and comparing frames of the present input speech to the representative frames of the reduced word template according to the number of frames combined in the representative frames of the reduced word template. In doing so, a measure of similarity between the present input speech and the word template is generated.

公开(公告)号：HK19297A

公开(公告)日：1997-02-20

申请号：HK19297

申请日：1997-02-20

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H03G3/34 ,  H04R25/00 ,  H04R27/00

Abstract: An improved noise suppression system (400) which performs speech quality enhancement upon speech-plus-noise signal available at the input (205) to generate a clean speech signal at the output (265) by spectral gain modification. The noise suppression system includes a background noise estimator (420) which generates and stores an estimate of the background noise power spectral density based upon pre-processed speech (215), as determined by the detected minima of the post-processed speech energy level. This post-processed speech (255) may be obtained directly from the output of the noise supression system, or may be simulated by multiplying the pre-processed speech energy (225) by the channel gain values of the modification signal (245). The channel gain controller (240) produces these individual channel gain values for application to both the channel gain modifier (250) and the background noise estimator (420). Each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The technique of implementing post-processed signal to generate the background noise estimate (325) provides a more accurate measurement of the background noise energy since it is based upon much cleaner speech signal. As a result, the present invention performs acoustic noise suppression in high ambient noise backgrounds with significantly less voice quality degradation.

公开(公告)号：FI870642A0

公开(公告)日：1987-02-16

申请号：FI870642

申请日：1987-02-16

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H03G3/34 ,  H04R25/00 ,  H04R27/00 ,  H03G

Abstract: An improved noise suppression system (400) which performs speech quality enhancement upon speech-plus-noise signal available at the input (205) to generate a clean speech signal at the output (265) by spectral gain modification. The noise suppression system includes a background noise estimator (420) which generates and stores an estimate of the background noise power spectral density based upon pre-processed speech (215), as determined by the detected minima of the post-processed speech energy level. This post-processed speech (255) may be obtained directly from the output of the noise supression system, or may be simulated by multiplying the pre-processed speech energy (225) by the channel gain values of the modification signal (245). The channel gain controller (240) produces these individual channel gain values for application to both the channel gain modifier (250) and the background noise estimator (420). Each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The technique of implementing post-processed signal to generate the background noise estimate (325) provides a more accurate measurement of the background noise energy since it is based upon much cleaner speech signal. As a result, the present invention performs acoustic noise suppression in high ambient noise backgrounds with significantly less voice quality degradation.

公开(公告)号：FI870642A

公开(公告)日：1987-02-16

申请号：FI870642

申请日：1987-02-16

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H03G3/34 ,  H04R25/00 ,  H04R27/00 ,  H03G

Abstract: An improved noise suppression system (400) which performs speech quality enhancement upon speech-plus-noise signal available at the input (205) to generate a clean speech signal at the output (265) by spectral gain modification. The noise suppression system includes a background noise estimator (420) which generates and stores an estimate of the background noise power spectral density based upon pre-processed speech (215), as determined by the detected minima of the post-processed speech energy level. This post-processed speech (255) may be obtained directly from the output of the noise supression system, or may be simulated by multiplying the pre-processed speech energy (225) by the channel gain values of the modification signal (245). The channel gain controller (240) produces these individual channel gain values for application to both the channel gain modifier (250) and the background noise estimator (420). Each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The technique of implementing post-processed signal to generate the background noise estimate (325) provides a more accurate measurement of the background noise energy since it is based upon much cleaner speech signal. As a result, the present invention performs acoustic noise suppression in high ambient noise backgrounds with significantly less voice quality degradation.

公开(公告)号：FI92118B

公开(公告)日：1994-06-15

申请号：FI870642

申请日：1987-02-16

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H03G3/34 ,  H04R25/00 ,  H04R27/00

Abstract: An improved noise suppression system (400) which performs speech quality enhancement upon speech-plus-noise signal available at the input (205) to generate a clean speech signal at the output (265) by spectral gain modification. The noise suppression system includes a background noise estimator (420) which generates and stores an estimate of the background noise power spectral density based upon pre-processed speech (215), as determined by the detected minima of the post-processed speech energy level. This post-processed speech (255) may be obtained directly from the output of the noise supression system, or may be simulated by multiplying the pre-processed speech energy (225) by the channel gain values of the modification signal (245). The channel gain controller (240) produces these individual channel gain values for application to both the channel gain modifier (250) and the background noise estimator (420). Each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The technique of implementing post-processed signal to generate the background noise estimate (325) provides a more accurate measurement of the background noise energy since it is based upon much cleaner speech signal. As a result, the present invention performs acoustic noise suppression in high ambient noise backgrounds with significantly less voice quality degradation.

公开(公告)号：DE3688614D1

公开(公告)日：1993-07-29

申请号：DE3688614

申请日：1986-12-18

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS ,  SMANSKI PHILIP JEROME

IPC: G10L11/00 ,  A61K35/14 ,  A61K38/00 ,  A61P31/12 ,  A61P35/00 ,  C07K1/20 ,  C07K14/395 ,  C07K14/52 ,  C07K14/54 ,  C12N15/09 ,  C12P21/02 ,  C12R1/865 ,  G10L15/06 ,  G10L15/10 ,  G10L15/18 ,  G10L5/00

Abstract: Described herein, is an arrangement and method for processing speech information in a speech recognition system (300). In such a system where the speech information is depicted as words, each word representing a sequence of frames (510) and where the recognition system has means (120) for comparing present input speech to a word template, the word template stored in template memory and derived from one or more previous input word, the present invention is best employed. The invention describes combining contiguous acoustically similar frames (512) derived from the previous input word or words into representative frames to form a corresponding reduced word template, storing the reduced word template in template memory in an efficient manner, and comparing frames of the present input speech to the representative frames of the reduced word template according to the number of frames combined in the representative frames of the reduced word template. In doing so, a measure of similarity between the present input speech and the word template is generated.

公开(公告)号：HK40496A

公开(公告)日：1996-03-15

申请号：HK40496

申请日：1996-03-07

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS ,  SMANSKI PHILIP JEROME

IPC: G10L11/00 ,  A61K35/14 ,  A61K38/00 ,  A61P31/12 ,  A61P35/00 ,  C07K1/20 ,  C07K14/395 ,  C07K14/52 ,  C07K14/54 ,  C12N15/09 ,  C12P21/02 ,  C12R1/865 ,  G10L15/06 ,  G10L15/10 ,  G10L15/18 ,  G10L5/00

Abstract: Described herein, is an arrangement and method for processing speech information in a speech recognition system (300). In such a system where the speech information is depicted as words, each word representing a sequence of frames (510) and where the recognition system has means (120) for comparing present input speech to a word template, the word template stored in template memory and derived from one or more previous input word, the present invention is best employed. The invention describes combining contiguous acoustically similar frames (512) derived from the previous input word or words into representative frames to form a corresponding reduced word template, storing the reduced word template in template memory in an efficient manner, and comparing frames of the present input speech to the representative frames of the reduced word template according to the number of frames combined in the representative frames of the reduced word template. In doing so, a measure of similarity between the present input speech and the word template is generated.

公开(公告)号：FI92118C

公开(公告)日：1994-09-26

申请号：FI870642

申请日：1987-02-16

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H03G3/34 ,  H04R25/00 ,  H04R27/00

公开(公告)号：EP0249635A4

公开(公告)日：1988-08-29

申请号：EP87900590

申请日：1986-12-18

Applicant: MOTOROLA INC

Inventor： GERSON IRA ALAN ,  LINDSLEY BRETT LOUIS ,  SMANSKI PHILIP JEROME

IPC: G10L11/00 ,  A61K35/14 ,  A61K38/00 ,  A61P31/12 ,  A61P35/00 ,  C07K1/20 ,  C07K14/395 ,  C07K14/52 ,  C07K14/54 ,  C12N15/09 ,  C12P21/02 ,  C12R1/865 ,  G10L15/06 ,  G10L15/10 ,  G10L15/18 ,  G10L5/00

CPC classification number: G10L15/063 ,  C07K2319/02

Abstract: Arrangement and method for processing speech information in a speech recognition system. In such a system where the speech information is depicted as words, each word representing a sequence of frames and where the recognition system has means for comparing present input speech to a word template, the word template stored in template memory (160) and derived from one or more previous input word, the present invention is best employed. The invention describes combining (322) contiguous acoustically similar frames derived from the previous input word or words into representative frames to form a corresponding reduced word template, storing the reduced word template in template memory (160) in an efficient manner, and comparing (326) frames of the present input speech to the representative frames of the reduced word template according to the number of frames combined in the representative frames of the reduced word template. In doing so, a measure of similarity between the present input speech and the word template is generated.

公开(公告)号：EP0226613A4

公开(公告)日：1988-06-14

申请号：EP86903767

申请日：1986-05-05

Applicant: MOTOROLA INC

Inventor： BORTH DAVID EDWARD ,  GERSON IRA ALAN ,  VILMUR RICHARD JOSEPH ,  SMANSKI PHILIP JEROME

IPC: G10K11/178 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/27 ,  H04R25/00 ,  H04R27/00 ,  H03G3/34

CPC classification number: G10L21/0208 ,  G10L25/27 ,  G10L2021/02168 ,  H04R25/505 ,  H04R27/00 ,  H04R2225/43

Abstract: An improved noise suppression system (400) which performs speech quality enhancement upon speech-plus-noise signal available at the input (205) to generate a clean speech signal at the output (265) by spectral gain modification. The noise suppression system includes a background noise estimator (420) which generates and stores an estimate of the background noise power spectral density based upon pre-processed speech (215), as determined by the detected minima of the post-processed speech energy level. This post-processed speech (255) may be obtained directly from the output of the noise supression system, or may be simulated by multiplying the pre-processed speech energy (225) by the channel gain values of the modification signal (245). The channel gain controller (240) produces these individual channel gain values for application to both the channel gain modifier (250) and the background noise estimator (420). Each individual channel gain value is selected as a function of (a) the channel number, (b) the current channel SNR estimate, and (c) the overall average background noise level. The technique of implementing post-processed signal to generate the background noise estimate (325) provides a more accurate measurement of the background noise energy since it is based upon much cleaner speech signal. As a result, the present invention performs acoustic noise suppression in high ambient noise backgrounds with significantly less voice quality degradation.