摘要:
An audio signal separation apparatus for separating observation signals in the time domain of a mixture of a plurality of signals including audio signals into individual signals by means of independent component analysis to produce isolated signals adapted to produce isolated signals in the time-frequency domain from the observation signals in the time-frequency domain and a separation matrix substituted by initial values, compute the modified value of the separation matrix by using a score function using the isolated signals in the time-frequency domain and a multidimensional probability density function and the separation matrix, modify the separation matrix until the separation matrix substantially converges by using the modified value and produce isolated signals in the time-frequency domain by using the substantially converging separation matrix.
摘要:
The present invention provides an apparatus for separating audio signals that can dissolve the problem of permutation when separating the plurality of mixed signals by independent component analysis. There is provided an audio signal separation apparatus for separating observation signals in a time domain of a mixture of a plurality of signals including audio signals into individual signals by means of independent component analysis to produce isolated signals, the apparatus including a first conversion section that converts the observation signals in the time domain into observation signals in a time-frequency domain, a separation section that produces isolated signals in a time-frequency domain from the observation signals in the time-frequency domain, and a second conversion section that converts the isolated signals in the time-frequency domain into isolated signals in a time domain, the separation section being adapted to produce isolated signals in a time-frequency domain from the observation signals in the time-frequency domain and a separation matrix substituted by initial values, compute the modified value of the separation matrix by using a score function using the isolated signals in the time-frequency domain and a multidimensional probability density function and the separation matrix, modify the separation matrix until the separation matrix substantially converges by using the modified value and produce isolated signals in the time-frequency domain by using the substantially converging separation matrix.
摘要:
A dialgue apparatus for interacting by outputting a response sentence in response to an input sentence includes a formal response acquisition unit configured to acquire a formal response sentence in response to the input sentence, a practical response acquisition unit configured to acquire a practical response sentence in response to the input sentence, and an output control unit configured to control outputting of the formal response sentence and the practical response sentence such that a conclusive response sentence is output in response to the input sentence.
摘要:
In a conventional voice dialogue system, there is a case where it is difficult to perform a natural dialogue with the user. Therefore, we designed to perform speech recognition on the user's utterance, to control a dialogue with the user according to a scenario previously given, based on the speech recognition result to generate an answering sentence corresponding to the contents of the user's utterance as the occasion demands, and to perform voice synthesis processing to one sentence in the reproduced scenario or the generated answering sentence.
摘要:
Problems of permutation can be solved with high accuracy without utilizing knowledge about original signals or information concerning positions of microphones and the like when each one of plural signals mixed in an audio signal is separated using independent component analysis. A short-time Fourier transformation section generates spectrograms of observation signals from observation signals in time domain. A signal separation section separates the spectrograms of the observation signals into spectrograms of respective signals, to generate spectrograms of separate signals. A permutation problem solution section calculates a scale corresponding to the degree of permutation, e.g., a Kullback-Leiblar information amount calculated by use of a multidimensional probability density function or multidimensional kurtosis, from substantial whole of the spectrograms of the separate signals. Based on the scale, signals at each of frequencies bin of the spectrograms of the separate signals are exchanged between channels, to solve the permutation problem.
摘要:
Problems of permutation can be solved with high accuracy without utilizing knowledge about original signals or information concerning positions of microphones and the like when each one of plural signals mixed in an audio signal is separated using independent component analysis. A short-time Fourier transformation section generates spectrograms of observation signals from observation signals in time domain. A signal separation section separates the spectrograms of the observation signals into spectrograms of respective signals, to generate spectrograms of separate signals. A permutation problem solution section calculates a scale corresponding to the degree of permutation, e.g., a Kullback-Leiblar information amount calculated by use of a multidimensional probability density function or multidimensional kurtosis, from substantial whole of the spectrograms of the separate signals. Based on the scale, signals at each of frequencies bin of the spectrograms of the separate signals are exchanged between channels, to solve the permutation problem.
摘要:
An information processing system stores information of various types, which is obtained in the real world, in connection with keys indicative of the attribute and feature of the information so that the real-world information is stored quickly and surely in the virtual world which is formed of the linkage of information and stored information of various types is retrieved easily.
摘要:
A signal processing apparatus includes: a learning processing unit that finds a separating matrix for separating mixed signals in which outputs from a plurality of sound sources are mixed, by a learning process that applies ICA (Independent Component Analysis) to observed signals including the mixed signals; a separation processing unit that applies the separating matrix to the observed signals to separate the mixed signals and generate separated signals corresponding to each of the sound sources; and a sound source direction estimating unit that computes a sound source direction of each of the generated separated signals. The sound source direction estimating unit calculates cross-covariance matrices between the observed signals and the separated signals in corresponding time segments in time-frequency domain, computes phase differences between elements of the cross-covariance matrices, and computes a sound source direction corresponding to each of the separated signals by applying the computed phase differences.
摘要:
A natural language processing apparatus includes an input section for inputting natural language, a representation converting section for converting representation of the natural language, a display section for displaying, for confirmation, sentence converted at the representation converting section, a machine translation section for carrying out machine translation of the confirmed sentence, and a control section for controlling these respective sections, thus to provide natural language processing in which confirmation operation of user is reduced.
摘要:
A signal processing apparatus includes a source separation module for producing respective separation signals corresponding to a plurality of sound sources by applying an ICA (Independent Component Analysis) to observation signals produced based on mixture signals from the sound sources, which are taken by source separation microphones, to thereby execute a separation process of the mixture signals, and a signal projection-back module for receiving observation signals of projection-back target microphones and the separation signals produced by the source separation module, and for producing projection-back signals as respective separation signals corresponding to the sound sources, which are taken by the projection-back target microphones. The signal projection-back module produces the projection-back signals by receiving the observation signals of the projection-back target microphones which differ from the source separation microphones.