Abstract: Provided are a noise reduction system that highly precisely estimates noise contained in an input signal and highly precisely reduces the noise contained in the input signal using the estimated noise, a speech detection system, a speech recognition system, a noise reduction method, and a noise reduction program.

Abstract: A voice response apparatus, method and non-transitory computer-readable storage medium are disclosed. The voice response apparatus may include a memory storing instructions, and one or more processors configured to process the instructions to detect an input voice from an input signal using a first frequency bandwidth, output a response voice including predetermined amount of components of a second frequency bandwidth, and set the first frequency bandwidth so that the first frequency bandwidth and the second frequency bandwidth do not overlap each other.

Abstract: A plurality of pruning measures (PM) are calculated from a feature amount (CV) of test data (TD) which is input, a plurality of isopycnic surfaces (EC) are plotted and set on a threshold space (SS), a threshold curved surface (SC) in which a decrease in at least one of a plurality of pruning measures (PM) causes an increase in at least one thereof is generated using a portion of one isopycnic surface (EC) as a part, a hypothesis curved surface (HC) of subject data (CD) is generated on the threshold space (SS) to set a position intersecting the threshold curved surface (SC) to a pruning threshold (PS), and a plurality of hypotheses of the subject data (CD) are pruned. Thereby, there is provided a data processing device of which at least one of the recognition speed and the recognition accuracy is higher than in the related art.

Abstract: This device 301 stores a first content-specific language model representing a probability that a specific word appears in a word sequence representing a first content, and a second content-specific language model representing a probability that the specific word appears in a word sequence representing a second content. Based on a first probability parameter representing a probability that a content represented by a target word sequence included in a speech recognition hypothesis generated by a speech recognition process of recognizing a word sequence corresponding to a speech, a second probability parameter representing a probability that the content represented by the target word sequence is a second content, the first content-specific language model and the second content-specific language model, the device creates a language model representing a probability that the specific word appears in a word sequence corresponding to a part corresponding to the target word sequence of the speech.

Abstract: A speech recognition apparatus that performs frame synchronous beam search by using a language model score look-ahead value prevents the pruning of a correct answer hypothesis while suppressing an increase in the number of hypotheses. A language model score look-ahead value imparting device 108 is provided with a word dictionary 203 that defines a phoneme string of a word, a language model 202 that imparts a score of appearance easiness of a word, and a smoothing language model score look-ahead value calculation means 201. The smoothing language model score look-ahead value calculation means 201 obtains a language model score look-ahead value at each phoneme in the word from the phoneme string of the word defined by the word dictionary 203 and the language model score defined by the language model 202 so that the language model score look-ahead values are prevented from concentrating on the beginning of the word.

Abstract: The present invention enables the recognition process at high speed even when a lot of garbage is included in the grammar. The first voice recognition processing unit generates a recognition hypothesis graph which indicates a structure of hypothesis that is derived according to a first grammar together with a score associated with respective connections of a recognition unit by executing a voice recognition process based on the first grammar to a voice feature amount of input voice, and the second voice recognition processing unit outputs the recognition result from a total score of a hypothesis which is derived according to a second grammar after executing a voice recognition process according to the second grammar that is specified to accept a section other than keywords in input voice as the garbage section to a voice feature amount of input voice, and the second voice recognition processing unit acquires the structure and the score of the garbage section from the recognition hypothesis graph.

Abstract: A voice recognition device that recognizes a voice of an input voice signal, comprises a voice model storage unit that stores in advance a predetermined voice model having a plurality of detail levels, the plurality of detail levels being information indicating a feature property of a voice for the voice model; a detail level selection unit that selects a detail level, closest to a feature property of an input voice signal, from the detail levels of the voice model stored in the voice model storage unit; and a parameter setting unit that sets parameters for recognizing the voice of an input voice according to the detail level selected by the detail level selection unit.

Abstract: A speech recognition device has: hypothesis search means which searches for an optimal solution of inputted speech data by generating a hypothesis which is a bundle of words which are searched for as recognition result candidates; self-repair decision means which calculates a self-repair likelihood of a word or a word sequence included in the hypothesis which is being searched for by the hypothesis search means, and decides whether or not self-repair of the word or the word sequence is performed; and transparent word hypothesis generation means which, when the self-repair decision means decides that the self-repair is performed, generates a transparent word hypothesis which is a hypothesis which regards as a transparent word a word or a word sequence included in an un-repaired interval related to the word or the word sequence, and the hypothesis search means searches hypotheses for an optimal solution, the hypotheses including as search target hypotheses the transparent word hypothesis generated by the transp

Abstract: A speech recognition system has: hypothesis search means which searches for an optimal solution of inputted speech data by generating a hypothesis which is a bundle of words which are searched for as recognition result candidates; self-repair decision means which calculates a self-repair likelihood of a word or a word sequence included in the hypothesis which is being searched for by the hypothesis search means, and decides whether or not self-repair of the word or the word sequence is performed; and transparent word hypothesis generation means which, when it is decided that the self-repair is performed, generates a transparent word hypothesis which is a hypothesis which regards as a transparent word a word or a word sequence included in a disfluency interval or a repair interval of a self-repair interval including the word or the word sequence.

Abstract: Provided is a text processing system capable of avoiding declining processing efficiency in analyses of text that does not contain breaks. This text processing system comprises: a linking means for generating linking data that links acquired text after the link object analysis result, which are the results of the analysis of text acquired prior to the acquired text; an analysis means for carrying out language analysis on the linked data, using at least a portion of the link object analysis result; and a determination means for determining a prescribed unit break included in the linked data, on the basis of the results of the analysis by the analysis means. The link object analysis results are the results of the analysis after the break that is determined by the determination means. The link object analysis results are the results of the analysis after the break that is determined by the determination means.

Abstract: A plurality of pruning measures (PM) are calculated from a feature amount (CV) of test data (TD) which is input, a plurality of isopycnic surfaces (EC) are plotted and set on a threshold space (SS), a threshold curved surface (SC) in which a decrease in at least one of a plurality of pruning measures (PM) causes an increase in at least one thereof is generated using a portion of one isopycnic surface (EC) as a part, a hypothesis curved surface (HC) of subject data (CD) is generated on the threshold space (SS) to set a position intersecting the threshold curved surface (SC) to a pruning threshold (PS), and a plurality of hypotheses of the subject data (CD) are pruned. Thereby, there is provided a data processing device of which at least one of the recognition speed and the recognition accuracy is higher than in the related art.

Abstract: A distance calculation unit (16) obtains the acoustic distance between the feature amount of input speech and each phonetic model. A word search unit (17) performs a word search based on the acoustic distance and a language model including the phoneme and prosodic label of a word, and outputs a word hypothesis and a first score representing the likelihood of the word hypothesis. The word search unit (17) also outputs a vowel interval and its tone label in the input speech, when assuming that the recognition result of the input speech is the word hypothesis. A tone recognition unit (21) outputs a second score representing the likelihood of the tone label output from the word search unit (17) based on a feature amount corresponding to the vowel interval output from the word search unit (17). A rescore unit (22) corrects the first score of the word hypothesis output from the word search unit (17) using the second score output from the tone recognition unit (21).

Abstract: A speech recognition unit (102) includes a phrase determination unit (103) which determines a phrase boundary based on the comparison between the hypothetical word group generated by speech recognition and set words representing phrase boundaries. In this speech processing device, the speech recognition unit (102) outputs recognition results for each phrase based on a phrase boundary determined by the phrase determination unit (103).

Abstract: This device 301 stores a first content-specific language model representing a probability that a specific word appears in a word sequence representing a first content, and a second content-specific language model representing a probability that the specific word appears in a word sequence representing a second content. Based on a first probability parameter representing a probability that a content represented by a target word sequence included in a speech recognition hypothesis generated by a speech recognition process of recognizing a word sequence corresponding to a speech, a second probability parameter representing a probability that the content represented by the target word sequence is a second content, the first content-specific language model and the second content-specific language model, the device creates a language model representing a probability that the specific word appears in a word sequence corresponding to a part corresponding to the target word sequence of the speech.

Abstract: A model adaptation device includes a text database that stores a plurality of sentences containing predetermined phonemes; a sentence list that includes a plurality of sentences that describe the contents of the input voice; an input unit to which the input voice is input; a model adaptation unit that performs the model adaptation using the input voice and the sentence list and outputs adapting characteristic information, which is for making the model approximate to the input voice; a statistic database that stores the adapting characteristic information; a distance calculation unit that outputs a value of an acoustic distance between the adapting characteristic information and the model for each phoneme; a phoneme detection unit that outputs a distance value, among the distance values, which is greater than a threshold value as a detection result; and a label generation unit that extracts from the text database a sentence containing a phoneme associated with the detection result and outputs the sentence.

Abstract: A distance calculation unit (16) obtains the acoustic distance between the feature amount of input speech and each phonetic model. A word search unit (17) performs a word search based on the acoustic distance and a language model including the phoneme and prosodic label of a word, and outputs a word hypothesis and a first score representing the likelihood of the word hypothesis. The word search unit (17) also outputs a vowel interval and its tone label in the input speech, when assuming that the recognition result of the input speech is the word hypothesis. A tone recognition unit (21) outputs a second score representing the likelihood of the tone label output from the word search unit (17) based on a feature amount corresponding to the vowel interval output from the word search unit (17). A rescore unit (22) corrects the first score of the word hypothesis output from the word search unit (17) using the second score output from the tone recognition unit (21).

Abstract: A speech recognition apparatus that performs frame synchronous beam search by using a language model score look-ahead value prevents the pruning of a correct answer hypothesis while suppressing an increase in the number of hypotheses. A language model score look-ahead value imparting device 108 is provided with a word dictionary 203 that defines a phoneme string of a word, a language model 202 that imparts a score of appearance easiness of a word, and a smoothing language model score look-ahead value calculation means 201. The smoothing language model score look-ahead value calculation means 201 obtains a language model score look-ahead value at each phoneme in the word from the phoneme string of the word defined by the word dictionary 203 and the language model score defined by the language model 202 so that the language model score look-ahead values are prevented from concentrating on the beginning of the word.

Abstract: The present invention enables the recognition process at high speed even when a lot of garbage is included in the grammar. The first voice recognition processing unit generates a recognition hypothesis graph which indicates a structure of hypothesis that is derived according to a first grammar together with a score associated with respective connections of a recognition unit by executing a voice recognition process based on the first grammar to a voice feature amount of input voice, and the second voice recognition processing unit outputs the recognition result from a total score of a hypothesis which is derived according to a second grammar after executing a voice recognition process according to the second grammar that is specified to accept a section other than keywords in input voice as the garbage section to a voice feature amount of input voice, and the second voice recognition processing unit acquires the structure and the score of the garbage section from the recognition hypothesis graph.

Abstract: A voice recognition system has a recognition dictionary storing voice information, a primary voice recognition means for performing primary voice recognition in response to input voice information pronounced by a user by the use of the recognition dictionary, and a recognition result judging means for deciding whether the primary voice recognition result is to be accepted or rejected. The voice recognition system includes a transceiver means for sending the input voice information of the user to an additional voice recognition means when the primary voice recognition result is rejected by the recognition result decision means and for receiving a secondary voice recognition result produced as a result of secondary voice recognition of the additional voice recognition means, and a recognition result output means for outputting the primary or secondary voice recognition result to an exterior of the voice recognition system.

Abstract: A service value calculation system includes: crisis problem inspection means which detects a crisis or a problem of a service object; and virtual damage amount calculation means which calculates a virtual damage amount generated if a detected crisis or problem is not solved when a service is not applied and calculates the service value.