Method, apparatus and computer program for detecting voice uttered from a particular position
An information processing apparatus includes a voice acquisition section, a reliability generation section, and a processing execution section. The voice acquisition section acquires an ambient voice. The reliability generation section generates reliability indicating a degree in which the acquired voice is uttered from the particular position on the basis of a predetermined transfer characteristic. As the predetermined transfer characteristic, a phase difference or acoustic characteristic of the voice can be assumed. The processing execution section executes a process according to the generated reliability. As the process according to the reliability, a notification according to the reliability or a predetermined command can be assumed to be executed.
1. An information processing apparatus comprising:
a voice acquisition section configured to acquire an ambient voice, the voice acquisition section including a plurality of microphones; and
processing circuitry configured to:
generate a reliability indicating a degree to which the acquired voice is uttered from a predetermined position relative to the plurality of microphones on a basis of a predetermined transfer characteristic, wherein generating the reliability includes searching for the acquired voice only in a direction of the predetermined position relative to the plurality of microphones by performing eigenvalue decomposition only with respect to the predetermined position and generating an evaluation function in which weighted normalization according to a contribution rate of a signal subspace is performed on a spatial spectrum; and
execute a process according to the reliability.
2. The information processing apparatus according to claim 1 , wherein
the processing circuitry is configured to generate the reliability on a basis of a phase difference of the voice acquired by the plurality of microphones as the predetermined transfer characteristic.
3. The information processing apparatus according to claim 2 , wherein
at least a part of the plurality of microphones are arranged in a vicinity of the predetermined position.
4. The information processing apparatus according to claim 2 , wherein
any one pair of the plurality of microphones is arranged at the predetermined position in an opposed manner to each other.
5. The information processing apparatus according to claim 1 , wherein
the processing circuitry is configured to generate the reliability on a basis of an acoustic characteristic of the acquired voice as the predetermined transfer characteristic.
6. The information processing apparatus according to claim 1 , wherein
the processing circuitry is configured to perform a notification according to the reliability.
7. The information processing apparatus according to claim 6 , wherein
the processing circuitry is configured to perform the notification indicating whether or not the voice is uttered from the predetermined position.
8. The information processing apparatus according to claim 6 , wherein
the processing circuitry is configured to perform the notification that it is impossible to determine whether or not the voice is uttered from the predetermined position.
9. The information processing apparatus according to claim 6 , wherein
the information processing apparatus is a mounting type terminal, and the processing circuitry is configured to perform the notification regarding a wearing condition.
10. The information processing apparatus according to claim 1 , wherein
the voice is uttered from the predetermined position, and the processing circuitry is configured to execute a predetermined command.
11. A method for processing a voice acquired by a plurality of microphones, the method executed by processing circuitry and comprising:
generating a reliability indicating a degree to which the acquired voice is uttered from a predetermined position relative to the plurality of microphones on a basis of a predetermined transfer characteristic, wherein generating the reliability includes searching for the acquired voice only in a direction of the predetermined position relative to the plurality of microphones by performing eigenvalue decomposition only with respect to the predetermined position and generating an evaluation function in which weighted normalization according to a contribution rate of a signal subspace is performed on a spatial spectrum; and
executing a process according to the reliability.
12. A non-transitory computer readable medium containing instructions that, when executed by processing circuitry, perform a method for processing a voice acquired by a plurality of microphones, the method comprising:
generating a reliability indicating a degree to which the acquired voice is uttered from a predetermined position relative to the plurality of microphones on a basis of a predetermined transfer characteristic, wherein generating the reliability includes searching for the acquired voice only in a direction of the predetermined position relative to the plurality of microphones by performing eigenvalue decomposition only with respect to the predetermined position and generating an evaluation function in which weighted normalization according to a contribution rate of a signal subspace is performed on a spatial spectrum; and
executing a process according to the reliability.