Abstract: This invention provides a voiced sound interval detection device which enables appropriate detection of a voiced sound interval of an observation signal even when a volume of sound from a sound source varies or when the number of sound sources is unknown or when different kinds of microphones are used together.

Abstract: A speaker identification device includes: a primary speaker identification unit that computes, for each pre-stored registered speaker, a score that indicates the similarity between input speech and speech of the registered speakers; a similar speaker selection unit that selects a plurality of the registered speakers as similar speakers according to the height of the scores thereof; a learning unit that creates a classifier for each similar speaker by sorting the speech of a certain similar speaker among the similar speakers as a positive instance and the speech of the other similar speakers as negative instances; and a secondary speaker identification unit that computes, for each classifier, a score of the classifier with respect to the input speech, and outputs an identification result.

Abstract: This conversation analysis device comprises: a change detection unit that detects, for each of a plurality of conversation participants, each of a plurality of prescribed change patterns for emotional states, on the basis of data corresponding to voices in a target conversation; an identification unit that identifies, from among the plurality of prescribed change patterns detected by the change detection unit, a beginning combination and an ending combination, which are prescribed combinations of the prescribed change patterns that satisfy prescribed position conditions between the plurality of conversation participants; and an interval determination unit that determines specific emotional intervals, which have a start time and an end time and represent specific emotions of the conversation participants of the target conversation, by determining a start time and an end time on the basis of each time position in the target conversation pertaining to the starting combination and ending combination identified by

Abstract: An analysis object determination device includes a detection unit which detects a plurality of specific utterance sections using data related to a voice in a conversation, the specific utterance sections representing a plurality of specific events originating from one or a plurality of participants in the conversation, or a specific event originating from one of the conversation participants, and an object determination unit which determines, on the basis of the plurality of specific utterance sections detected by the detection unit, one or more cause analysis sections for the specific event originating from the conversation participant, the number of the cause analysis sections being fewer than the number of the plurality of specific utterance sections.

Abstract: This dissatisfying conversation determination device include: a data acquisition unit that acquires a plurality of word data, and a plurality of phonation time data by target conversation participants; an extraction unit that extracts a plurality of specific word data configuring polite expression and impolite expression from the plurality of word data; a change detection unit that detects a point of change from polite expression to impolite expression by the target conversation participants based on the plurality of specific word data and the plurality of phonation time data; and a dissatisfaction determination unit that determines whether the target conversation is a dissatisfying conversation for the target conversation participants based on the result of the point of change detected by the change detection unit.

Abstract: An expression classification device includes: a segment detection unit that detects a specific expression segment that includes a specific expression that can be used in a plurality of nuances from data corresponding to a voice of a conversation; a feature extraction unit that extracts feature information that includes at least one of a prosody feature and an utterance timing feature with regard to the specific expression segment that is detected by the segment detection unit; and a classification unit that classifies the specific expression included in the specific expression segment based on a nuance corresponding to a use situation in the conversation by using the feature information extracted by the feature extraction unit.

Abstract: An information retrieval system including: a calculating unit which calculates a query language model that is a language model of an input word or of a set of input words; an extracting unit which refers to a storage means storing a result of speech recognition on speech data which is speech-recognized with use of a speech recognition language model, and extracting a result indicating a high degree of similarity to the query language model from the result, as matching data; a first updating unit which updates the speech recognition language model with use of the matching data; and a second updating unit which updates the result stored in the storage means, with use of the updated speech recognition language model, wherein the extracting means extracts a result indicating a high degree of similarity to the query language model from the updated result, and outputs a retrieval result indicating data associated with the extracted result.

Abstract: A method for processing multichannel acoustic signals which is characterized by calculating the feature quantity of each channel from the input signals of a plurality of channels, calculating similarity between the channels in the feature quantity of each channel, selecting channels having high similarity, and separating signals using the input signals of the selected channels.

Abstract: A method for processing multichannel acoustic signals which processes input signals of a plurality of channels including the voices of a plurality of speaking persons. The method is characterized by detecting the voice section of each speaking person or each channel, detecting overlapped sections wherein the detected voice sections are common between channels, determining a channel to be subjected to crosstalk removal and the section thereof by use of at least voice sections not including the detected overlapped sections, and removing crosstalk in the sections of the channel to be subjected to the crosstalk removal.

Abstract: A method for processing multichannel acoustic signals, whereby input signals of a plurality of channels including the voices of a plurality of speaking persons are processed. The method is characterized by comprising: calculating the first feature quantity of the input signals of the multichannels for each channel; calculating similarity of the first feature quantity of each channel between the channels; selecting channels having high similarity; separating signals using the input signals of the selected channels; inputting the input signals of the channels having low similarity and the signals after the signal separation; and detecting a voice section of each speaking person or each channel.

Abstract: Speech recognition of even a speaker who uses a speech recognition system is enabled by using an extended recognition dictionary suited to the speaker without requiring any previous learning using an utterance label corresponding to the speech of the speaker.

Abstract: A language model learning system for learning a language model on an identifiable basis relating to a word error rate used in speech recognition. The language model learning system (10) includes a recognizing device (101) for recognizing an input speech by using a sound model and a language model and outputting the recognized word sequence as the recognition result, a reliability degree computing device (103) for computing the degree of reliability of the word sequence, and a language model parameter updating device (104) for updating the parameters of the language model by using the degree of reliability. The language model parameter updating device updates the parameters of the language model to heighten the degree of reliability of the word sequence the computed degree of reliability of which is low when the recognizing device recognizes by using the updated language model and the reliability degree computing device computes the degree of reliability.

Abstract: The present invention uses a language model creation device 200 that creates a new language model using a standard language model created from standard language text. The language model creation device 200 includes a transformation rule storage section 201 that stores transformation rules used for transforming dialect-containing word strings into standard language word strings, and a dialect language model creation section 203 that creates dialect-containing n-grams by applying the transformation rules to word n-grams in the standard language model and, furthermore, creates the new language model (dialect language model) by adding the created dialect-containing n-grams to the word n-grams.

Abstract: A method and apparatus for carrying out adaptation using input speech data information even at a low reference pattern recognition performance. A reference pattern adaptation device 2 includes a speech recognition section 18, an adaptation data calculating section 19 and a reference pattern adaptation section 20. The speech recognition section 18 calculates a recognition result teacher label from the input speech data and the reference pattern. The adaptation data calculating section 19 calculates adaptation data composed of a teacher label and speech data. The adaptation data is composed of the input speech data and the recognition result teacher label corrected for adaptation by the recognition error knowledge which is the statistical information of the tendency towards recognition errors of the reference pattern. The reference pattern adaptation section 20 adapts the reference pattern using the adaptation data to generate an adaptation pattern.

Abstract: Acoustic models and language models are learned according to a speaking length which indicates a length of a speaking section in speech data, and speech recognition process is implemented by using the learned acoustic models and language models. A speech recognition apparatus includes means (103) for detecting a speaking section in speech data (101) and for generating a section information which indicates the detected speaking section, means (104) for recognizing a data part corresponding to a section information in the speech data as well as text data (102) written from the speech data and for classifying the data part based on a speaking length thereof, and means (106) for learning acoustic models and language models (107) by using the classified data part (105).

Abstract: The voiced sound interval classification device comprises a vector calculation unit which calculates, from a power spectrum time series of voice signals, a multidimensional vector series as a vector series of a power spectrum having as many dimensions as the number of microphones, a difference calculation unit which calculates, with respect to each time of the multidimensional vector series, a vector of a difference between the time and the preceding time, a sound source direction estimation unit which estimates, as a sound source direction, a main component of the differential vector, and a voiced sound interval determination unit which determines whether each sound source direction is in a voiced sound interval or a voiceless sound interval by using a predetermined voiced sound index indicative of a likelihood of a voiced sound interval of the voice signal applied at each time.

Abstract: This invention provides a voiced sound interval detection device which enables appropriate detection of a voiced sound interval of an observation signal even when a volume of sound from a sound source varies or when the number of sound sources is unknown or when different kinds of microphones are used together.

Abstract: A weighting factor learning system includes an audio recognition section that recognizes learning audio data and outputting the recognition result; a weighting factor updating section that updates a weighting factor applied to a score obtained from an acoustic model and a language model so that the difference between a correct-answer score calculated with the use of a correct-answer text of the learning audio data and a score of the recognition result becomes large; a convergence determination section that determines, with the use of the score after updating, whether to return to the weighting factor updating section to update the weighting factor again; and a weighting factor convergence determination section that determines, with the use of the score after updating, whether to return to the audio recognition section to perform the process again and update the weighting factor using the weighting factor updating section.

Abstract: To enable selection of a speaker, the acoustic feature value of which is similar to that of an utterance speaker, with accuracy and stability, while adapting to changes even when the acoustic feature value of the speaker changes every moment, a long-time speaker score is calculated (log likelihood of each of a plurality of speaker models stored in a speaker model storage with respect to the acoustic feature value) based on an arbitrary number of utterances, for example, and a short-time speaker score is calculated based on a short-time utterance, for example. Speakers are selected corresponding to a predetermined number of speaker models having a high long-time speaker score. Speakers are selected corresponding to the speaker models, the number of which is smaller than the predetermined number and the short-time speaker sore of which is high, from among the speakers having a high long-time speaker score.

Abstract: A speech recognition apparatus (110) selects an optimum recognition result from recognition results output from a set of speech recognizers (s1-sM) based on a majority decision. This decision is implemented with taking into account weight values, as to the set of the speech recognizers, learned by a learning apparatus (100). The learning apparatus includes a unit (103) selecting speech recognizers corresponding to characteristics of speech for learning (101), a unit (104) finding recognition results of the speech for learning by using the selected speech recognizers, a unit (105) unifying the recognition results and generating a word string network, and a unit (106) finding weight values concerning a set of the speech recognizers by implementing learning processing.