摘要:
A speech recognition system according to the present invention includes a sound source separating section which separates mixed speeches from multiple sound sources from one another; a mask generating section which generates a soft mask which can take continuous values between 0 and 1 for each frequency spectral component of a separated speech signal using distributions of speech signal and noise against separation reliability of the separated speech signal; and a speech recognizing section which recognizes speeches separated by the sound source separating section using soft masks generated by the mask generating section.
摘要:
Robotics visual and auditory system is provided which is made capable of accurately conducting the sound source localization of a target by associating a visual and an auditory information with respect to a target. It is provided with an audition module (20), a face module (30), a stereo module (37), a motor control module (40), an association module (50) for generating streams by associating events from said each module (20, 30, 37, and 40), and an attention control module (57) for conducting attention control based on the streams generated by the association module (50), and said association module (50) generates an auditory stream (55) and a visual stream (56) from a auditory event (28) from the auditory module (20), a face event (39) from the face module (30), a stereo event (39a) from the stereo module (37), and a motor event (48) from the motor control module (40), and an association stream (57) which associates said streams, as well as said audition module (20) collects sub-bands having the interaural phase difference (IPD) or the interaural intensity difference (IID) within the preset range by an active direction pass filter (23a) having a pass range which, according to auditory characteristics, becomes minimum in the frontal direction, and larger as the angle becomes wider to the left and right, based on an accurate sound source directional information from the association module (50), and conducts sound source separation by restructuring the wave shape of the sound source.
摘要:
A musical score position estimating device includes an audio signal acquiring unit, a musical score information acquiring unit acquiring musical score information corresponding to an audio signal acquired by the audio signal acquiring unit, an audio signal feature extracting unit extracting a feature amount of the audio signal, a musical score feature extracting unit extracting a feature amount of the musical score information, a beat position estimating unit estimating a beat position of the audio signal, and a matching unit matching the feature amount of the audio signal with the feature amount of the musical score information using the estimated beat position to estimate a position of a portion in the musical score information corresponding to the audio signal.
摘要:
A reverberation suppressing apparatus separating sound source signals based on input signals output from microphones collecting the plurality of sound source signals, includes a sound signal output unit generating sound signals and outputting the generated sound signals, a sound acquiring unit acquiring the input signals from microphones, a first evaluation function calculation unit calculating a separation matrix, the input signals, and the sound source signals, and calculating a first evaluation function, a reverberation component suppressing unit calculating an optimal separation matrix, and suppressing a reverberation component by separating the sound source signals other than the generated sound signals, and a separation matrix updating unit dividing a step-size function, approximating each segment to a linear function, calculating step sizes based on the approximated linear functions, and repeatedly updating the separation matrix so that the degree of separation of the sound source signals exceeds the predetermined value.
摘要:
The speech recognition system of the present invention includes: a sound source separating section which separates mixed speeches from multiple sound sources; a mask generating section which generates a soft mask which can take continuous values between 0 and 1 for each separated speech according to reliability of separation in separating operation of the sound source separating section; and a speech recognizing section which recognizes speeches separated by the sound source separating section using soft masks generated by the mask generating section.
摘要:
A robot visuoauditory system that makes it possible to process data in real time to track vision and audition for an object, that can integrate visual and auditory information on an object to permit the object to be kept tracked without fail and that makes it possible to process the information in real time to keep tracking the object both visually and auditorily and visualize the real-time processing is disclosed. In the system, the audition module (20) in response to sound signals from microphones extracts pitches therefrom, separate their sound sources from each other and locate sound sources such as to identify a sound source as at least one speaker, thereby extracting an auditory event (28) for each object speaker. The vision module (30) on the basis of an image taken by a camera identifies by face, and locate, each such speaker, thereby extracting a visual event (39) therefor. The motor control module (40) for turning the robot horizontally. extracts a motor event (49) from a rotary position of the motor. The association module (60) for controlling these modules forms from the auditory, visual and motor control events an auditory stream (65) and a visual stream (66) and then associates these streams with each other to form an association stream (67). The attention control module (6) effects attention control designed to make a plan of the course in which to control the drive motor, e.g., upon locating the sound source for the auditory event and locating the face for the visual event, thereby determining the direction in which each speaker lies. The system also includes a display (27, 37, 48, 68) for displaying at least a portion of auditory, visual and motor information. The attention control module (64) servo-controls the robot on the basis of the association stream or streams.
摘要:
A robot may include a driving control unit configured to control a driving of a movable unit that is connected movably to a body unit, a voice generating unit configured to generate a voice, and a voice output unit configured to output the voice, which has been generated by the voice generating unit. The voice generating unit may correct the voice, which is generated, based on a bearing of the movable unit, which is controlled by the driving control unit, to the body unit.
摘要:
A musical score position estimating apparatus includes a sound feature quantity generating unit configured to generate a feature quantity of an input sound signal, and, a score position estimating unit configured to calculate a weight coefficient based on the feature quantity of the sound signal and a feature quantity of musical score information and estimates a musical score position using a virtual musical score position and a virtual tempo corresponding to the weight coefficient.
摘要:
It is a robotics visual and auditory system provided with an auditory module (20), a face module (30), a stereo module (37), a motor control module (40), and an association module (50) to control these respective modules. The auditory module (20) collects sub-bands having interaural phase difference (IPD) or interaural intensity difference (IID) within a predetermined range by an active direction pass filter (23a) having a pass range which, according to auditory characteristics, becomes minimum in the frontal direction, and larger as the angle becomes wider to the left and right, based on an accurate sound source directional information from the association module (50), and conducts sound source separation by restructuring a wave shape of a sound source, conducts speech recognition of separated sound signals from respective sound sources using a plurality of acoustic models (27d), integrates speech recognition results from each acoustic model by a selector, and judges the most reliable speech recognition result among the speech recognition results.
摘要:
A first domain satisfying a first condition concerning a current utterance understanding result and a second domain satisfying a second condition concerning a selection history are specified. For each of the first and second domains, indices representing reliability in consideration of the utterance understanding history, selection history, and utterance generation history are evaluated. Based on the evaluation results, one of the first, second, and third domains is selected as a current domain according to a selection rule.