Speech processing system, speech processing method, speech processing program, vehicle including speech processing system on board, and microphone placing method

• US 9,905,243 B2
• Filed: 01/16/2014
• Issued: 02/27/2018
• Est. Priority Date: 05/23/2013
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Tsujikawa, Masanori, Hanazawa, Ken, Sugiyama, Akihiko
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): KIM, JONATHAN C
• Application Number:
  US14/892,396
• Publication Number:
  US 20160111109A1
• Time in Patent Office: 1,503 Days
• Field of Search: None
• CPC Class Codes: B60R 11/0247 for microphones or earphones
• CPC Class Codes: B60R 2011/0028 Ceiling, e.g. roof rails
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: H04R 2227/001 Adaptation of signal processing in PA systems in dependence of presence of noise
• CPC Class Codes: H04R 2499/13 Acoustic transducers and sound field adaptation in vehicles
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407

Abstract

A system of this invention is directed to a speech processing system that efficiently performs noise suppression processing for a plurality of noise sources spreading in a lateral direction with respect to a speaker of interest. The speech processing system includes a microphone array including a plurality of microphones, each of which inputs a sound mixture including speech of a speaker of interest and noise from a noise source region including a plurality of noise sources placed in a lateral direction with respect to the speaker of interest, and outputs a mixture signal including a speech signal and a noise signal, the plurality of microphones being arranged such that a difference between respective distances from the plurality of microphones to the speaker of interest becomes different from a difference between respective distances from the plurality of microphones to the noise source region, and a noise suppressor that suppresses the noise based on the mixture signals output from the plurality of microphones.

Claims

1. A speech processing system comprising:

at least one hardware processor configured to implement;

a linear microphone array comprising a plurality of microphones, arranged on a straight line, each of which inputs speech of a speaker of interest and noise from a noise source region comprising a plurality of noise sources, and outputs a mixture signal comprising said speech and said noise; and

a noise suppressor that suppresses said noise based on said mixture signals,

wherein a direction of arranging the plurality of microphones in said linear microphone array is determined such that said straight line is perpendicular to a longitudinal axis of said noise source region, and

a distance, between said linear microphone array and said noise source region, and a tilt of a placement plane of said microphone array are adjusted so as to decrease differences between respective distances from each of noise sources in said noise source region to the plurality of microphones in said linear microphone array.

2. The speech processing system according to claim 1, wherein said linear microphone array comprises not less than three microphones arranged on a straight line, and

the at least one hardware processor is further configured to implement:

a selector that selects, out of the not less than three microphones, microphones to output the mixture signals used by said noise suppressor.

3. The speech processing system according to claim 2, wherein said selector selects, out of the not less than three microphones, microphones to output the mixture signals used by said noise suppressor in accordance with a type of driven noise sources.

4. The speech processing system according to claim 2, wherein said selector selects, out of the not less than three microphones, microphones to output the mixture signals used by said noise suppressor in accordance with a position of the speaker of interest.

5. The speech processing system according to claim 2, wherein said selector selects, out of the not less than three microphones, microphones to output the mixture signals used by said noise suppressor in accordance with a frequency of the noise generated from the noise source region.

6. The speech processing system according to claim 2, wherein said selector selects, out of the not less than three microphones, microphones to output the mixture signals used by said noise suppressor in accordance with a frequency of noise generated from a noise source placed outside the noise source region.

7. The speech processing system according to claim 1, further comprising, in addition to said linear microphone array, at least two microphones arranged in a direction approximately perpendicular to a direction in which the plurality of microphones are arranged in said linear microphone array;

and

wherein said selector selects, in accordance with noise from a lateral direction to the direction in which the plurality of microphones are arranged, the at least two microphones that are arranged in the direction perpendicular to the direction in which the plurality of microphones are arranged.

8. The speech processing system according to claim 1, wherein an interval between microphones in said linear microphone array is less than 10 cm and falls within a range of 2 cm to 4 cm.

9. The speech processing system according to claim 1, wherein the speaker of interest, the noise source region, and the linear microphone array exist in a closed space, and

said linear microphone array is placed on a ceiling of the closed space.

10. The speech processing system according to claim 9, wherein the closed space is a space in a vehicle,

said linear microphone array is placed on a ceiling above a sun visor, and

portions of the sun visor overlapping the microphones are processed to pass a sound so as to prevent the sun visor from blocking the sound to the microphones of said linear microphone array.

11. A speech processing system comprising:

at least one hardware processor configured to implement;

a first microphone that is placed on a ceiling in a vehicle, inputs a sound mixture comprising noise from a noise source region comprising a plurality of noise sources and a voice of a passenger of the vehicle, and outputs a first mixture signal;

a second microphone that is placed on the ceiling in the vehicle such that a straight line, on which the first microphone and the second microphone are placed, of a linear microphone array, comprising the first microphone and the second microphone, is perpendicular to a longitudinal axis of said noise source region, inputs a sound mixture comprising the noise from the noise source region and the voice of the passenger of the vehicle, and outputs a second mixture signal; and

a noise suppressor that outputs an enhanced speech signal based on the first mixture signal and the second mixture signal,

wherein a distance, between said linear microphone array and said noise source region, and a tilt of a placement plane of said microphone array are adjusted so as to decrease differences between respective distances from each of noise sources in said noise source region to the first microphone and the second microphone in said linear microphone array.

12. A vehicle comprising the speech processing system according to claim 11.

13. A microphone placing method comprising:

arranging on a straight line a plurality of microphones, each of which inputs a sound mixture, comprising speech of a speaker of interest and noise from a noise source region comprising a plurality of noise sources, and outputs a mixture signal comprising a speech signal and a noise signal,

wherein the plurality of microphones are of a linear microphone array and are arranged on the straight line perpendicular to a longitudinal axis of said noise source region, and

a distance, between said linear microphone array and said noise source region, and a tilt of a placement plane of said microphone array are adjusted so as to decrease differences between respective distances from each of noise sources in said noise source region to the plurality of microphones in said linear microphone array.

14. A speech processing method comprising:

at least one hardware processor configured to implement;

selecting microphones, to output a plurality of mixture signals comprising a speech signal and a noise signal, out of a plurality of microphones, each of which inputs a sound mixture, comprising speech of the speaker of interest and noise from a noise source region comprising a plurality of noise sources, and outputs the mixture signal, the selected microphones are of a linear microphone array and are arranged on a straight line perpendicular to a longitudinal axis of said noise source region; and

suppressing the noise based on the mixture signals output from the selected microphones, and

wherein a distance, between said linear microphone array and said noise source region, and a tilt of a placement plane of said microphone array are adjusted so as to decrease differences between respective distances from each of noise sources in said noise source region to the plurality of microphones in said linear microphone array.

15. A non-transitory computer readable storage medium storing a speech processing program for causing a computer to execute a method, comprising:

implementing by at least one hardware processor;

selecting microphones, to output a plurality of mixture signals comprising a speech signal and a noise signal, out of a plurality of microphones, each of which inputs a sound mixture, comprising speech of the speaker of interest and noise from a noise source region comprising a plurality of noise sources, and outputs the mixture signal, the selected microphones are of a linear microphone array and are arranged on a straight line perpendicular to a longitudinal axis of said noise source region; and

suppressing the noise based on the mixture signals output from the selected microphones,

wherein a distance, between said linear microphone array and said noise source region, and a tilt of a placement plane of said microphone array are adjusted so as to decrease differences between respective distances from each of noise sources in said noise source region to the plurality of microphones in said linear microphone array.