摘要:
Disclosed is a noise model generation device that generates a noise model suitable for each environment by determining whether an sound source of a detection target is included in sound information collected by an sound collector with high accuracy. The noise model generation device generates a noise model relating to noise information other than the sound source of the detection target included in the sound information collected by the sound collector, which acquires a power spectrum from the sound information; determines whether the sound source of the detection target is included in the sound information collected by evaluating a probability density distribution (histogram) of the power spectrum; and generates a noise model from the collected sound information when it is determined that the sound source of the detection target is not included in the collected sound information.
摘要:
A sound source detecting system that detects a predetermined sound source on the basis of sounds collected by sound collectors includes: a noise extracting unit that extracts a noise from signals of the collected sounds; and a noise suppressing unit that suppresses a signal component of the noise extracted by the noise extracting unit from the signals of the collected sounds. The sound source detecting unit detects a location of the predetermined sound source, such as an approaching vehicle, using information about the sounds having the signals of which the noise is suppressed.
摘要:
A language storage method according to one aspect of the present invention includes vectorization steps for vectorizing language accumulated in a dialog log database using a word vector created in advance for each word; determination step for determining whether to employ the language that has been vectorized as response data; and a storage step for accumulating the language that has been determined to be employed as the response data in a response database, in which a dimension reduction step for reducing the number of dimensions of the vector of the language vectorized in the vectorization step is included between the vectorization step and the determination step, and in the determination step, it is determined which one of an employed group and an unemployed group the vector of the language whose number of dimensions has been reduced in the dimension reduction step belongs to.
摘要:
To provide a microphone unit capable of acquiring a target sound with high accuracy. A microphone unit in accordance with an exemplary embodiment of the present invention includes a plurality of microphones, a microphone substrate on which the plurality of microphones are mounted, and a vibration observation device disposed at roughly a center of gravity of a shape that is formed by connecting centers of certain adjacent microphones among the plurality of microphones.
摘要:
Provided are a signal separating apparatus and a signal separating method capable of solving the permutation problem and separating user speech to be extracted. The signal separating apparatus separates a specific speech signal and a noise signal from a received sound signal. First, a joint probability density distribution estimation unit of a permutation solving unit calculates joint probability density distributions of the respective separated signals. Then, a classifying determination unit of the permutation solving unit determines classifying based on shapes of the calculated joint probability density distributions.
摘要:
A mobile body control device includes: a brain activity detecting unit that detects brain activity information of a user; a brain signal separating unit that separates an artifact component from the brain activity information detected by the brain activity detecting unit; a control signal generating unit that slides a sampling period for extracting brain data, at predetermined intervals in an overlapped manner in the brain activity information from which the artifact component is separated, successively calculates feature values for the brain data within each of the sampling periods obtained by sliding, and generates a control signal based on the feature values calculated; and a drive control unit that drives and controls a mobile body with a user riding thereon, based on the control signal generated.
摘要:
Provided are a signal separating apparatus and a signal separating method capable of solving the permutation problem and separating user speech to be extracted. The signal separating apparatus separates a specific speech signal and a noise signal from a received sound signal. First, a joint probability density distribution estimation unit of a permutation solving unit calculates joint probability density distributions of the respective separated signals. Then, a classifying determination unit of the permutation solving unit determines classifying based on shapes of the calculated joint probability density distributions.