Nippon Telegraph and Telephone Corporation

Satoshi Kobashikawa

Hosana Kamiyama

Atsushi Ando

Ryo Masumura

Atsunori Ogawa

Yusuke Ijima

Yushi Aono

Naohiro Tawara

Paralinguistic information is estimated with high accuracy even when an utterance for which it is difficult to identify paralinguistic information is used for model learning. An acoustic feature extraction unitextracts an acoustic feature from an utterance. An anti-teacher decision unitdecides, based on a paralinguistic information label indicating a determination result of paralinguistic information given by a plurality of listeners for each utterance, an anti-teacher label indicating an anti-teacher serving as incorrect paralinguistic information for the utterance. An anti-teacher estimation model learning unitlearns, based on an acoustic feature extracted from the utterance and the anti-teacher label, an anti-teacher estimation model for outputting a posterior probability of anti-teacher for an input acoustic feature.

Paralinguistic information estimation model learning apparatus, paralinguistic information estimation apparatus, and program

An estimation apparatus clusters a group of voice signals including a voice signal having a speaker attribute to be estimated into a plurality of clusters. Subsequently, the estimation apparatus identifies, from the plurality of clusters, a cluster to which the voice signal to be estimated belongs. Next, the estimation apparatus uses a speaker attribute estimation model to estimate speaker attributes of respective voice signals in the identified cluster. After that, the estimation apparatus estimates an attribute of the entire cluster, by using an estimation result of the speaker attributes of the voice signals in the identified cluster, and outputs an estimation result of the speaker attribute of the entire cluster, as an estimation result of the speaker attribute of the voice signal to be estimated.

Estimation device, estimation method, and estimation program

To increase the accuracy of paralinguistic information estimation. A paralinguistic information estimation model storage unitstores a paralinguistic information estimation model outputting, with a plurality of independent features as inputs, paralinguistic information estimation results. A feature extraction unitextracts the features from an input utterance. A paralinguistic information estimation unitestimates paralinguistic information of the input utterance from the features extracted from the input utterance, by using the paralinguistic information estimation model. The paralinguistic information estimation model includes, for each of the features, a feature sub-model outputting information to be used for estimation of paralinguistic information, based only on the feature, for each of the features, a feature weight calculation unit calculating a feature weight, based on an output result of the feature sub-model, for each of the features, a feature gate weighting the output result from the feature sub-model with the feature weight and outputting a result, and a result integration sub-model estimating the paralinguistic information, based on output results from all the feature gates.

Paralinguistic information estimation apparatus, paralinguistic information estimation method, and program

An attribute identification technology that can reject an attribute identification result if the reliability thereof is low is provided. An attribute identification device includes: a posteriori probability calculation unitthat calculates, from input speech, a posteriori probability sequence {q(c, i)} which is a sequence of the posteriori probabilities q(c, i) that a frame i of the input speech is a class c; a reliability calculation unitthat calculates, from the posteriori probability sequence {q(c, i)}, reliability r(c) indicating the extent to which the class c is a correct attribute identification result; and an attribute identification result generating unitthat generates an attribute identification result L of the input speech from the posteriori probability sequence {q(c, i)} and the reliability r(c). The attribute identification result generating unitobtains a most probable estimated class c{circumflex over (&#x2003;)}, which is a class that is estimated to be the most probable attribute, from the posteriori probability sequence {q(c, i)} and sets &#x3d5; indicating rejection as the attribute identification result L if the reliability r(c{circumflex over (&#x2003;)}) of the most probable estimated class c{circumflex over (&#x2003;)} falls within a predetermined range indicating that the reliability r(c{circumflex over (&#x2003;)}) is low and sets the most probable estimated class c{circumflex over (&#x2003;)} as the attribute identification result L otherwise.

Attribute identification method, and program

The present invention provides a pronunciation error detection apparatus capable of following a text without the need for a correct sentence even when erroneous recognition such as a reading error occurs. The pronunciation error detection apparatus comprises: a speech recognition part that recognizes the speech in speech data based on a speech recognition model for a non-native speaker, and outputs speech recognition results, reliability and time information; a reliability determination part that outputs the speech recognition results with higher reliability than a predetermined threshold and the corresponding time information as the determined speech recognition results and the determined time information; and a pronunciation error detection part that outputs a phoneme as a pronunciation error when reliability for each phoneme in the speech recognition results using the native speaker speech recognition model under a weakly constraining grammar is greater than the reliability of the corresponding phoneme in the speech recognition results using the native speaker acoustic model under a constraining grammar in which the determined speech recognition results are correct for the speech data in a segment specified by the determined time information.

Pronunciation error detection apparatus, pronunciation error detection method and program

Estimation accuracies of a conversation satisfaction and a speech satisfaction are improved. A learning data storage unit () stores learning data including a conversation voice containing a conversation including a plurality of speeches, a correct answer value of a conversation satisfaction for the conversation, and a correct answer value of a speech satisfaction for each speech included in the conversation. A model learning unit () learns a satisfaction estimation model using a feature quantity of each speech extracted from the conversation voice, the correct answer value of the speech satisfaction, and the correct answer value of the conversation satisfaction, the satisfaction estimation model configured by connecting a speech satisfaction estimation model part that receives a feature quantity of each speech and estimates the speech satisfaction of each speech with a conversation satisfaction estimation model part that receives at least the speech satisfaction of each speech and estimates the conversation satisfaction.

Satisfaction estimation model learning apparatus, satisfaction estimating apparatus, satisfaction estimation model learning method, satisfaction estimation method, and program

With correct emotion classes selected as correct values of an emotion of an utterer of a first utterance from among a plurality of emotion classes C, . . . , Cby listeners who have listened to the first utterance, as an input, the numbers of times nthat emotion classes Chave been selected as the correct emotion classes are obtained, and rates of the numbers of times nto a sum total of the numbers of times n, . . . , nor smoothed values of the rates are obtained as correct emotion soft labels tcorresponding to the first utterance.

Label generation device, model learning device, emotion recognition apparatus, methods therefor, program, and recording medium

State-of-satisfaction change pattern models each including a set of transition weights in state sequences of the states of satisfaction are obtained for predetermined change patterns of the states of satisfaction, and a state-of-satisfaction estimation model for obtaining the posteriori probability of the utterance feature amount given the state of satisfaction of an utterer is obtained by using the utterance-for-learning feature amount and a correct value of the state of satisfaction of an utterer who gave an utterance for learning corresponding to the utterance-for-learning feature amount. By using the input utterance feature amount and the state-of-satisfaction change pattern models and the state-of-satisfaction estimation model, an estimated value of the state of satisfaction of an utterer who gave an utterance corresponding to the input utterance feature amount is obtained.

Model learning device, estimating device, methods therefor, and program

An urgency level estimation technique of estimating an urgency level of a speaker for free uttered speech, which does not require a specific word, is provided. An urgency level estimation apparatus includes a feature amount extracting part configured to extract a feature amount of an utterance from uttered speech, and an urgency level estimating part configured to estimate an urgency level of a speaker of the uttered speech from the feature amount based on a relationship between a feature amount extracted from uttered speech and an urgency level of a speaker of the uttered speech, the relationship being determined in advance, and the feature amount includes at least one of a feature indicating speaking speed of the uttered speech, a feature indicating voice pitch of the uttered speech and a feature indicating a power level of the uttered speech.

Growing community of inventors

Yokosuka, Japan

Satoshi Kobashikawa