SPEECH INPUT APPARATUS, SPEECH PROCESSING METHOD, SPEECH PROCESSING PROGRAM, CEILING MEMBER, AND VEHICLE

• US 20150380011A1
• Filed: 09/09/2013
• Published: 12/31/2015
• Est. Priority Date: 02/12/2013
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: TSUJIKAWA, Masanori, HANAZAWA, Ken, SUGIYAMA, Akihiko
• Granted Patent: US 9,972,336 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 2021/02165 Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: H04R 1/08 Mouthpieces; Microphones; Attachments therefor
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2410/03 Reduction of intrinsic noise in microphones
• 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

An apparatus of this invention is directed to a speech input apparatus for obtaining a piece of high-quality speech with included noise reduced. The speech input apparatus includes a sound insulating block attached to a ceiling member in a vehicle, a first microphone that is attached to a side surface of the sound insulating block or the ceiling member in the vicinity of the sound insulating block on a side close to a passenger of the vehicle, inputs a sound mixture including the voice of the passenger and noise in the vehicle, and outputs a first signal to a noise suppressor configured to output an enhanced speech signal, and a second microphone that is attached to a side surface of the sound insulating block or the ceiling member in the vicinity of the sound insulating block on a side far from the passenger, inputs the noise in the vehicle, and outputs a second signal to the noise suppressor.

Claims

1. A speech input apparatus comprising:

a sound insulating block attached to a ceiling member in a vehicle;

a first microphone that is attached to one of a side surface of said sound insulating block and the ceiling member in a vicinity of said sound insulating block on a side close to a passenger of the vehicle, inputs a sound mixture including a voice of the passenger and noise in the vehicle and outputs a first signal to a noise suppressor; and

a second microphone that is attached to one of a side surface of said sound insulating block and the ceiling member in the vicinity of said sound insulating block on a side far from the passenger, inputs the noise in the vehicle and outputs a second signal to the noise suppressor.

2. The speech input apparatus according to claim 1, wherein said sound insulating block is attached in a predetermined range of the ceiling member in which said sound insulating block does not separate the noise in the vehicle while insulating the voice of the passenger.

3. The speech input apparatus according to claim 1, wherein said sound insulating block has a triangular surface covering the ceiling member, said first microphone is arranged on a side of a base, and said second microphone is arranged on a side of an apex.

4. The speech input apparatus according to claim 1, wherein a vertical sectional shape of said sound insulating block is a right angled triangle whose one side other than a hypotenuse is located on the side of the ceiling member, said first microphone is arranged on the side of the hypotenuse, and said second microphone is arranged on another side other than the hypotenuse.

5. The speech input apparatus according to claim 1 further comprising a first mechanism capable of retracting said sound insulating block above the ceiling member.

6. The speech input apparatus according to claim 5, further comprising a first driver that operates said first mechanism based on a first control signal.

7. The speech input apparatus according to claim 6, wherein said first driver operates said first mechanism based on the first control signal generated based on information including one of a vehicle speed, an engine or motor speed, noise of an air conditioner, an operation of a windshield wiper, an operation of a blinker, an operation of an audio system, an operation of a car navigation system, and an operation of a hazard lamp.

8. The speech input apparatus according to claim 1, further comprising a second mechanism capable of rotating said sound insulating block about an axis that makes a right angle with respect to a lower surface of the ceiling member.

9. The speech input apparatus according to claim 8, further comprising a second driver that operates said second mechanism based on a second control signal.

10. The speech input apparatus according to claim 9, wherein said second driver operates said second mechanism based on the second control signal generated based on information including one of a piece of speech, a speech input direction, a seat weight sensor, and an instruction from a user.

11. The speech input apparatus according to claim 1, wherein a plurality of first microphones are arranged around or on side surfaces of said sound insulating block, and further comprising a switch that switches said plurality of first microphones corresponding to said second microphone.

12. The speech input apparatus according to claim 1, further comprising:

a plurality of speech input sets, each including said sound insulating block, said first microphone and said second microphone, at least one speech input set being provided for each seat; and

a selector that selects one of said plurality of speech input sets.

13. The speech input apparatus according to claim 12, wherein said selector selects one of said plurality of speech input sets based on a third control signal generated based on information including one of a speech analysis result, a detection result of a seat weight sensor and an instruction from a user.

16. A ceiling member comprising a speech input apparatus of claim 1.

17. A vehicle comprising a speech input apparatus of claim 1.

14. A speech processing method comprising:

by a first microphone that is provided on one of a side surface of a sound insulating block attached to a ceiling member in a vehicle and the ceiling member in a vicinity of the sound insulating block on a side close to a passenger of the vehicle, inputting a sound mixture including a voice of the passenger and noise in the vehicle and outputting a first signal to a noise suppressor; and

by a second microphone that is provided on one of a side surface of the sound insulating block attached to the ceiling member in the vehicle and the ceiling member in the vicinity of the sound insulating block on a side far from the passenger, inputting the noise in the vehicle and outputting a second signal to the noise suppressor; and

by the noise suppressor, suppressing the noise based on the first signal and the second signal and outputting an enhanced speech signal.

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

causing a first microphone that is provided on one of a side surface of a sound insulating block attached to a ceiling member in a vehicle and the ceiling member in a vicinity of the sound insulating block on a side close to a passenger of the vehicle, to input a sound mixture including a voice of the passenger and noise in the vehicle and output a first signal to a noise suppressor; and

causing a second microphone that is provided on one of a side surface of the sound insulating block attached to the ceiling member in the vehicle and the ceiling member in the vicinity of the sound insulating block on a side far from the passenger, to input the noise in the vehicle and output a second signal to the noise suppressor; and

causing the noise suppressor to suppress the noise based on the first signal and the second signal and output an enhanced speech signal.