Speech processing apparatus, control method thereof, storage medium storing control program thereof, and vehicle, information processing apparatus, and information processing system including the speech processing apparatus

• US 9,299,360 B2
• Filed: 12/03/2011
• Issued: 03/29/2016
• Est. Priority Date: 01/13/2011
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Arakawa, Takayuki, Sugiyama, Akihiko
• Primary Examiner(s): Opsasnick, Michael N
• Assistant Examiner(s): Lee, Kee Young
• Application Number:
  US13/979,596
• Publication Number:
  US 20130297303A1
• Time in Patent Office: 1,578 Days
• Field of Search: 704226-228, 704/275, 381/92, 381/94.1, 381/94.7, 381/71.1, 381/71.4, 381/86, 381/365, 381/389
• US Class Current: 1/1
• 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 21/0208 Noise filtering
• CPC Class Codes: H04R 1/342 for microphones
• CPC Class Codes: H04R 2410/05 Noise reduction with a separate noise microphone
• 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 speech processing apparatus acquires pseudo speech from a mixture of sound including desired speech and noise. A first microphone inputs a first mixture sound, including desired speech and noise, and outputs a first mixture signal. A second microphone opens to the sound space and is disposed at a focus position of an interface, that is part of a boundary of the sound space and has one of a quadratic surface shape and a pseudo surface shape approximating a quadratic surface, inputs a second mixture sound including the desired speech reflected by the interface and the noise reflected by the interface at a ratio different from the first mixture sound, and outputs a second mixture signal. A noise suppression circuit suppresses an estimated noise signal based on the first mixture signal and the second mixture signal and outputs a pseudo speech signal.

Claims

1. A speech processing apparatus located in a vehicle comprising:

a first microphone configured to input, from a sound space in the vehicle, a first mixture sound including desired speech uttered by an occupant in the vehicle and noise in the vehicle at a first ratio of the noise to the desired speech, and to output a first mixture signal;

a second microphone opened to said sound space in the vehicle and configured to be disposed at a focus position of an interface, said interface being one of a windshield and a rear window of the vehicle as part of a boundary of the sound space and having one of a quadratic surface shape and a pseudo surface shape as an aggregate of planes extending in tangential directions of a quadratic surface for collecting the noise in the vehicle at the focus position, the second microphone being configured to input a second mixture sound at the focus position including the desired speech uttered by the occupant in the vehicle and the noise in the vehicle reflected by the interface, at a second ratio of the reflected noise to the desired speech different from the first ratio, and to output a second mixture signal; and

a noise suppression circuit configured to suppress an estimated noise signal based on the first mixture signal and the second mixture signal, and to output a pseudo speech signal,

wherein said first microphone is disposed at a position farther from the interface than the focus position and nearer to the occupant uttering the desired speech than said second microphone, so that the second ratio is larger than the first ratio.

2. The speech processing apparatus according to claim 1, wherein said first microphone and said second microphone are provided as an integral speech input unit.

3. The speech processing apparatus according to claim 1, further comprising a sound insulator disposed in the vehicle and between said first microphone and said second microphone.

4. The speech processing apparatus according to claim 3, wherein said sound insulator is disposed at a position in the vehicle to prevent the desired speech and the noise from being directly input to said second microphone without being reflected by the interface.

5. The speech processing apparatus according to claim 1, further comprising an output unit that outputs, based on one of the pseudo speech signal, the estimated noise signal, and a parameter of said noise suppression circuit, information representing whether a position of said second microphone is a position to collect the noise in the vehicle.

6. The speech processing apparatus according to claim 1, wherein said noise suppression circuit comprises:

a first subtracter that subtracts the estimated noise signal estimated to be included in the first mixture signal from the first mixture signal;

a second subtracter that subtracts an estimated speech signal estimated to be included in the second mixture signal from the second mixture signal;

an estimated noise signal generator that generates the estimated noise signal from an output signal of said second subtracter; and

an estimated speech signal generator that generates the estimated speech signal from an output signal of said first subtracter, and

the pseudo speech signal is the output signal of said first subtracter.

7. An information processing system including a speech processing apparatus of claim 1, comprising:

a speech recognition apparatus that recognizes desired speech from the pseudo speech signal output from the speech processing apparatus; and

an information processing apparatus that processes information in accordance with the desired speech recognized by said speech recognition apparatus.

8. A control method of a speech processing apparatus located in a vehicle, comprising:

acquiring a first mixture signal converted from a first mixture sound including desired speech uttered by an occupant in the vehicle and noise in the vehicle, at a first ratio of the noise to the desired speech, in a first microphone that is disposed at a position farther from an interface than a focus position of the interface and near to a speaker giving the desired speech, said interface being one of a windshield and a rear window of the vehicle as a part of a boundary of a sound space in the vehicle and having one of a quadratic surface shape and a pseudo surface shape as an aggregate of planes extending in tangential directions of a quadratic surface for collection the noise in the vehicle at the focus position;

acquiring a second mixture signal converted from a second mixture sound including the desired speech uttered by the occupant in the vehicle and the noise in the vehicle collected at a focus position of said interface by said interface, at a second ratio of the noise to the desired speech larger than the first ratio, in a second microphone opened to said sound space and disposed at the focus position of said interface;

acquiring a pseudo speech signal and parameters from a noise suppression circuit that is configured to suppress an estimated noise signal based on the first mixture signal and the second mixture signal; and

notifying, based on the pseudo speech signal and the parameters, whether the position of the second microphone is the focus position of the interface in the vehicle.

9. A non-transitory computer-readable storage medium storing a control program of a speech processing apparatus located in a vehicle, the control program comprising:

acquiring a first mixture signal converted from a first mixture sound including desired speech uttered by an occupant in the vehicle and noise in the vehicle, at a first ratio of the noise to the desired speech, in a first microphone that is disposed at a position farther from an interface than a focus position of the interface and near to a speaker giving the desired speech, said interface being one of a windshield and a rear window of the vehicle as part of a boundary of a sound space in the vehicle and having one of a quadratic surface shape and a pseudo surface shape as an aggregate of planes extending in tangential directions of a quadratic surface for collecting the noise in the vehicle at the focus position;

acquiring a second mixture signal converted from a second mixture sound including the desired speech uttered by the occupant in the vehicle and the noise in the vehicle collected at a focus position of said interface by said interface, at a second ratio of the noise to the desired speech larger than the first ratio in a second microphone opened to said sound space and disposed at the focus position of said interface;

acquiring a pseudo speech signal and parameters from a noise suppression circuit that is configured to suppress an estimated noise signal based on the first mixture signal and the second mixture signal; and

notifying, based on the pseudo speech signal and the parameters, whether the position of the second microphone is the focus position of the interface in the vehicle.