Abstract: The present invention relates to a method, preprocessor, speech recognition system, and program product for extracting a target speech by removing noise. In an embodiment of the invention target speech is extracted from two input speeches, which are obtained through at least two speech input devices installed in different places in a space, applies a spectrum subtraction process by using a noise power spectrum (U?) estimated by one or both of the two speech input devices (X?(T)) and an arbitrary subtraction constant (?) to obtain a resultant subtracted power spectrum (Y?(T)). The invention further applies a gain control based on the two speech input devices to the resultant subtracted power spectrum to obtain a gain-controlled power spectrum (D?(T)). The invention further applies a flooring process to said resultant gain-controlled power spectrum on the basis of arbitrary Flooring factor (?) to obtain a power spectrum for speech recognition (Z?(T)).

Abstract: A speech signal processing system which outputs a speech feature, divides an input speech signal into frames so that each pair of consecutive frames have a frame shift length equal to at least one period of the speech signal and have an overlap equal to at least a predetermined length, applies discrete Fourier transform to each of the frames, calculates a CSP coefficient for the pair, searches a predetermined search range in which a speech wave lags a period equal to at least one period to obtain the maximum value of the CSP coefficient for the pair, and generates time-series data of the maximum CSP coefficient values arranged in the order in which the frames appear. A method and a computer readable article of manufacture for the implementing the same are also provided.

Abstract: Waveform concatenation speech synthesis with high sound quality. Prosody with both high accuracy and high sound quality is achieved by performing a two-path search including a speech segment search and a prosody modification value search. An accurate accent is secured by evaluating the consistency of the prosody by using a statistical model of prosody variations (the slope of fundamental frequency) for both of two paths of the speech segment selection and the modification value search. In the prosody modification value search, a prosody modification value sequence that minimizes a modified prosody cost is searched for. This allows a search for a modification value sequence that can increase the likelihood of absolute values or variations of the prosody to the statistical model as high as possible with minimum modification values.

Abstract: A speech feature extraction apparatus, speech feature extraction method, and speech feature extraction program. A speech feature extraction apparatus includes: first difference calculation module to: (i) receive, as an input, a spectrum of a speech signal segmented into frames for each frequency bin; and (ii) calculate a delta spectrum for each of the frame, where the delta spectrum is a difference of the spectrum within continuous frames for the frequency bin; and first normalization module to normalize the delta spectrum of the frame for the frequency bin by dividing the delta spectrum by a function of an average spectrum; where the average spectrum is an average of spectra through all frames that are overall speech for the frequency bin; and where an output of the first normalization module is defined as a first delta feature.

Abstract: Waveform concatenation speech synthesis with high sound quality. Prosody with both high accuracy and high sound quality is achieved by performing a two-path search including a speech segment search and a prosody modification value search. An accurate accent is secured by evaluating the consistency of the prosody by using a statistical model of prosody variations (the slope of fundamental frequency) for both of two paths of the speech segment selection and the modification value search. In the prosody modification value search, a prosody modification value sequence that minimizes a modified prosody cost is searched for. This allows a search for a modification value sequence that can increase the likelihood of absolute values or variations of the prosody to the statistical model as high as possible with minimum modification values.

Abstract: An information processing apparatus determines a weight of each physical feature for hierarchical clustering by acquiring training data of multiple pieces of content in triplets with label information indicating a pair specified by a user as having a highest degree of similarity among three contents of the triplet and executing hierarchical clustering using a feature vector of each piece of content of the training data and the weight of each feature to determine the hierarchical structure of the training data. The information processing apparatus updates the weight of each feature so that the degree of agreement between a pair combined first as being the same clusters among three contents of the triplet in a determined hierarchical structure and a pair indicated by label information corresponding to the triplet increases.

Abstract: A speech feature extraction apparatus, speech feature extraction method, and speech feature extraction program. A speech feature extraction apparatus includes: first difference calculation module to: (i) receive, as an input, a spectrum of a speech signal segmented into frames for each frequency bin; and (ii) calculate a delta spectrum for each of the frame, where the delta spectrum is a difference of the spectrum within continuous frames for the frequency bin; and first normalization module to normalize the delta spectrum of the frame for the frequency bin by dividing the delta spectrum by a function of an average spectrum; where the average spectrum is an average of spectra through all frames that are overall speech for the frequency bin; and where an output of the first normalization module is defined as a first delta feature.

Abstract: An information processing apparatus determines a weight of each physical feature for hierarchical clustering by acquiring training data of multiple pieces of content in triplets with label information indicating a pair specified by a user as having a highest degree of similarity among three contents of the triplet and executing hierarchical clustering using a feature vector of each piece of content of the training data and the weight of each feature to determine the hierarchical structure of the training data. The information processing apparatus updates the weight of each feature so that the degree of agreement between a pair combined first as being the same clusters among three contents of the triplet in a determined hierarchical structure and a pair indicated by label information corresponding to the triplet increases.

Abstract: An information processing apparatus, information processing method, and computer readable non-transitory storage medium for analyzing words reflecting information that is not explicitly recognized verbally. An information processing method includes the steps of: extracting speech data and sound data used for recognizing phonemes included in the speech data as words; identifying a section surrounded by pauses within a speech spectrum of the speech data; performing sound analysis on the identified section to identify a word in the section; generating prosodic feature values for the words; acquiring frequencies of occurrence of the word within the speech data; calculating a degree of fluctuation within the speech data for the prosodic feature values of high frequency words where the high frequency words are any words whose frequency of occurrence meets a threshold; and determining a key phrase based on the degree of fluctuation.

Abstract: An information processing apparatus, information processing method, and computer readable non-transitory storage medium for analyzing words reflecting information that is not explicitly recognized verbally. An information processing method includes the steps of: extracting speech data and sound data used for recognizing phonemes included in the speech data as words; identifying a section surrounded by pauses within a speech spectrum of the speech data; performing sound analysis on the identified section to identify a word in the section; generating prosodic feature values for the words; acquiring frequencies of occurrence of the word within the speech data; calculating a degree of fluctuation within the speech data for the prosodic feature values of high frequency words where the high frequency words are any words whose frequency of occurrence meets a threshold; and determining a key phrase based on the degree of fluctuation.

Abstract: A speech feature extraction apparatus, speech feature extraction method, and speech feature extraction program. A speech feature extraction apparatus includes: first difference calculation module to: (i) receive, as an input, a spectrum of a speech signal segmented into frames for each frequency bin; and (ii) calculate a delta spectrum for each of the frame, where the delta spectrum is a difference of the spectrum within continuous frames for the frequency bin; and first normalization module to normalize the delta spectrum of the frame for the frequency bin by dividing the delta spectrum by a function of an average spectrum; where the average spectrum is an average of spectra through all frames that are overall speech for the frequency bin; and where an output of the first normalization module is defined as a first delta feature.

Abstract: A position detection method, system, and computer readable article of manufacture tangibly embodying computer readable instructions for executing the method for detecting the position of a sound source using at least two microphones. The method includes the steps of: emitting a reproduced sound from the sound source; observing the reproduced sound and an observed sound at the microphones; converting the reproduced sound and the observed sound into electrical signals; transforming the signals of the reproduced sound and of the observed sound into frequency spectra by a frequency spectrum transformer apparatus; calculating Crosspower Spectrum Phase (CSP) coefficients of the frequency spectra of the signals by a CSP coefficient calculator apparatus; and calculating distances between the position of the sound source and the positions of the microphones based on the calculated CSP coefficients by a distance calculating apparatus, thereby detecting the position of the sound source.

Abstract: A system, method, and program product for processing voice data in a conversation between two persons to determine characteristic conversation patterns. The system includes: a variation calculator for calculating a variation of a speech ratio of a first speaker and a variation calculator for calculating a variation of a speech ratio of a second speaker; a difference calculator for calculating a difference data string; a smoother for generating a smoothed difference data string; and a presenter for presenting the difference between the variation of the speech ratio of the first speaker and the speech ratio of the second speaker. The method includes: calculating a variation of a speech ratio of a first speaker and a second speaker; calculating a difference data string; generating a smoothed difference data string; and grouping them according to their patterns.

Abstract: An example embodiment of the invention includes a speech recognition processing unit for specifying speech segments for speech data, recognizing a speech in each of the speech segments, and associating a character string of obtained recognition data with the speech data for each speech segment, based on information on a time of the speech, and an output control unit for displaying/outputting the text prepared by sorting the recognition data in each speech segment. Sometimes, the system further includes a text editing unit for editing the prepared text, and a speech correspondence estimation unit for associating a character string in the edited text with the speech data by using a technique of dynamic programming.

Abstract: A word prediction apparatus and method that improves the precision accuracy, and a speech recognition method and an apparatus therefor are provided. For the prediction of a sixth word “?”, a partial analysis tree having a modification relationship with the sixth word is predicted. “sara-ni sho-senkyoku no” has two partial analysis trees, “sara-ni” and “sho-senkyoku no”. It is predicted that “sara-ni” does not have a modification relationship with the sixth word, and that “sho-senkyoku no” does. Then, “donyu”, which is the sixth word from “sho-senkyoku no”, is predicted. In this example, since “sara-ni” is not useful information for the prediction of “donyu”, it is preferable that “donyu” be predicted only by “sho-senkyoku no”.

Abstract: An objective is to provide a technique for accurately reproducing features of a fundamental frequency of a target-speaker's voice on the basis of only a small amount of learning data. A learning apparatus learns shift amounts from a reference source F0 pattern to a target F0 pattern of a target-speaker's voice. The learning apparatus associates a source F0 pattern of a learning text to a target F0 pattern of the same learning text by associating their peaks and troughs. For each of points on the target F0 pattern, the learning apparatus obtains shift amounts in a time-axis direction and in a frequency-axis direction from a corresponding point on the source F0 pattern in reference to a result of the association, and learns a decision tree using, as an input feature vector, linguistic information obtained by parsing the learning text, and using, as an output feature vector, the calculated shift amounts.

Abstract: A speech signal processing system which outputs a speech feature, divides an input speech signal into frames so that each pair of consecutive frames have a frame shift length equal to at least one period of the speech signal and have an overlap equal to at least a predetermined length, applies discrete Fourier transform to each of the frames, calculates a CSP coefficient for the pair, searches a predetermined search range in which a speech wave lags a period equal to at least one period to obtain the maximum value of the CSP coefficient for the pair, and generates time-series data of the maximum CSP coefficient values arranged in the order in which the frames appear. A method and a computer readable article of manufacture for the implementing the same are also provided.

Abstract: Techniques for acquiring, from an input text and an input speech, a set of a character string and a pronunciation thereof which should be recognized as a word. A system according to the present invention: selects, from an input text, plural candidate character strings which are candidates to be recognized as a word; generates plural pronunciation candidates of the selected candidate character strings; generates frequency data by combining data in which the generated pronunciation candidates are respectively associated with the character strings; generates recognition data in which character strings respectively indicating plural words contained in the input speech are associated with pronunciations; and selects and outputs a combination contained in the recognition data, out of combinations each consisting of one of the candidate character strings and one of the pronunciation candidates.

Abstract: A speech recognition device and method configured to include a computer, for recognizing speech, including: a storage location for storing a feature quantity acquired from a speech signal for each frame; storage portions for storing acoustic model data and language model data; a echo speech component for generating echo speech model data from a speech signal acquired prior to a speech signal to be processed at the current time point and using the echo speech model data to generate adapted acoustic model data; and a processing component for utilizing the feature quantity, the adapted acoustic model data, and the language model data to provide a speech recognition result of the speech signal.

Abstract: A synthetic speech system includes a phoneme segment storage section for storing multiple phoneme segment data pieces; a synthesis section for generating voice data from text by reading phoneme segment data pieces representing the pronunciation of an inputted text from the phoneme segment storage section and connecting the phoneme segment data pieces to each other; a computing section for computing a score indicating the unnaturalness of the voice data representing the synthetic speech of the text; a paraphrase storage section for storing multiple paraphrases of the multiple first phrases; a replacement section for searching the text and replacing with appropriate paraphrases; and a judgment section for outputting generated voice data on condition that the computed score is smaller than a reference value and for inputting the text after the replacement to the synthesis section to cause the synthesis section to further generate voice data for the text.