Speech processing method and apparatus, storage medium, and speech system

• US 8,065,138 B2
• Filed: 08/31/2007
• Issued: 11/22/2011
• Est. Priority Date: 03/01/2005
• Status: Expired due to Fees

• Current Assignee: Japan Advanced Institute Of Science And Technology
• Original Assignee: Glory Limited, Japan Advanced Institute Of Science And Technology
• Inventors: Futonagane, Rieko, Akagi, Masato, Irie, Yoshihiro, Yanagiuchi, Hisakazu, Tanaka, Yoshitane
• Primary Examiner(s): CHAWAN, VIJAY B
• Application Number:
  US11/849,106
• Publication Number:
  US 20080281588A1
• Time in Patent Office: 1,544 Days
• Field of Search: 704/207, 704/205, 704/233, 704/209, 704/223, 704/267, 704/222, 704/219, 704/200.1, 704500-504, 704226-230, 704/263, 704/220
• US Class Current: 704/205
• CPC Class Codes: G10K 11/1754 Speech masking
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: G10L 21/0232 Processing in the frequency domain
• CPC Class Codes: G10L 21/0364 for improving intelligibility

Abstract

A speech processing apparatus includes a spectrum envelope extracting unit which extracts the spectrum envelope of an input speech signal, a spectrum envelope deforming unit which applies deformation to the spectrum envelope to generate a deformed spectrum envelope, a spectrum fine structure extracting unit which extracts the spectrum fine structure of the input speech signal, a deformed spectrum generating unit which generates a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure, and a speech generating unit which generates an output speech signal on the basis of the deformed spectrum. This apparatus emits a disrupting sound based on the output speech signal to prevent a third party from eavesdropping on a conversation.

Claims

1. A speech processing method comprising:

extracting a spectrum envelope of an input speech signal;

extracting a spectrum fine structure of the input speech signal for representing the sound source information of the input speech signal;

generating a deformed spectrum envelope by applying deformation to the spectrum envelope upon setting an inversion axis with respect to the spectrum envelope and inverting the spectrum envelope about the inversion axis;

generating a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure; and

generating an output speech signal on the basis of the deformed spectrum.

2. A speech processing method comprising:

extracting a spectrum envelope of an input speech signal;

extracting a spectrum fine structure of the input speech signal;

generating a deformed spectrum envelope by applying deformation to the spectrum envelope;

generating a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure;

extracting a high-frequency component of the spectrum of the input speech signal;

replacing a high-frequency component contained in the deformed spectrum by the extracted high-frequency component; and

generating an output speech signal on the basis of a deformed spectrum after replacement of the high-frequency component.

3. A speech processing apparatus comprising:

a spectrum envelope extracting unit which extracts a spectrum envelope of an input speech signal;

a spectrum fine structure extracting unit which extracts a spectrum fine structure of the input speech signal;

a spectrum envelope deforming unit which applies deformation to the spectrum envelope upon setting an inversion axis with respect to the spectrum envelope and inverting the spectrum envelope about the inversion axis to generate a deformed spectrum envelope;

a deformed spectrum generating unit which generates a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure; and

a speech generating unit which generates an output speech signal on the basis of the deformed spectrum.

4. A speech processing apparatus according to claim 3, wherein the spectrum envelope deforming unit is configured to apply the deformation to the spectrum envelope in at least one of an amplitude direction and a frequency axis direction.

5. A speech processing apparatus according to claim 3, wherein the spectrum envelope deforming unit is configured to apply the deformation by changing positions of peaks and dips of the spectrum envelope.

6. A speech processing apparatus according to claim 3, wherein the spectrum envelope deforming unit is configured to apply the deformation by shifting the spectrum envelope on a frequency axis.

7. A speech system comprising:

a microphone which captures conversational speech to obtain the input speech signal;

a speech processing apparatus defined in claim 3; and

a loudspeaker which emits a disrupting sound in accordance with the output speech signal.

8. A speech processing apparatus comprising:

a spectrum envelope extracting unit which extracts a spectrum envelope of an input speech signal;

a spectrum fine structure extracting unit which extracts a spectrum fine structure of the input speech signal;

a spectrum envelope deforming unit which applies deformation to the spectrum envelope to generate a deformed spectrum envelope;

a deformed spectrum generating unit which generates a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure;

a high-frequency component extracting unit which extracts a high-frequency component of the spectrum of the input speech signal;

a high-frequency component replacing unit which replaces a high-frequency component contained in the deformed spectrum by the high-frequency component extracted by the high-frequency extracting unit; and

a speech generating unit which generates an output speech signal on the basis of a deformed spectrum after replacement of the high-frequency component.

9. A speech processing apparatus according to claim 8, wherein the spectrum envelope deforming unit is configured to apply the deformation to the spectrum envelope in at least one of an amplitude direction and a frequency axis direction.

10. A speech processing apparatus according to claim 8, wherein the spectrum envelope deforming unit is configured to apply the deformation by changing positions of peaks and dips of the spectrum envelope.

11. A speech processing apparatus according to claim 8, wherein the spectrum envelope deforming unit is configured to apply the deformation by setting an inversion axis with respect to the spectrum envelope and inverting the spectrum envelope about the inversion axis.

12. A speech processing apparatus according to claim 8, wherein the spectrum envelope deforming unit is configured to apply the deformation by shifting the spectrum envelope on a frequency axis.

13. A speech processing apparatus according to claim 8, wherein the high-frequency component replacing unit sets a replacement band with respect to a high-frequency component extracted by the high-frequency component extracting unit and replaces the high-frequency component contained in the deformed spectrum by a high-frequency component in the replacement band.

14. A speech system comprising:

a microphone which captures conversational speech to obtain the input speech signal;

a speech processing apparatus according to claim 8; and

a loudspeaker which emits a disrupting sound in accordance with the output speech signal.

15. A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps comprising:

extracting a spectrum envelope of an input speech signal;

extracting a spectrum fine structure of the input speech signal;

generating a deformed spectrum envelope by applying deformation to the spectrum envelope upon setting an inversion axis with respect to the spectrum envelope and inverting the spectrum envelope about the inversion axis;

generating a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure; and

generating an output speech signal on the basis of the deformed spectrum.

16. A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps comprising:

extracting a spectrum envelope of an input speech signal;

extracting a spectrum fine structure of the input speech signal;

generating a deformed spectrum envelope by applying deformation to the spectrum envelope;

generating a deformed spectrum by combining the deformed spectrum envelope with the spectrum fine structure;

extracting a high-frequency component of the spectrum of the input speech signal;

replacing a high-frequency component contained in the deformed spectrum by the extracted high-frequency component; and

generating an output speech signal on the basis of a deformed spectrum after replacement of the high-frequency component.