Sony Corporation

Sony International (europe) Gmbh

Sony Electronics Inc

Helmut Lucke

Hiroaki Ogawa

Katsuki Minamino

Yasuharu Asano

Junichi Yamashita

Thomas Kemp

Keiichi Yamada

Xavier Menendez-Pidal

Ralf Kompe

Atsuo Hiroe

Masanori Omote

Hitoshi Honda

Hideshi Tamaru

Gustavo Hernandez-Abrego

Silke Goronzy

Peter Buchner

Yaeko Fujita

Stefan Rapp

Franck Giron

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.

Apparatus and method for separating audio signals

A speech recognition apparatus in which the accuracy in speech recognition is improved as the resource is prevented from increasing. Such a word which is probable as the result of the speech recognition is selected on the basis of an acoustic score and a linguistic score, while word selection is also performed on the basis of a measure different from the acoustic score, such as the number of phonemes being small, a part of speech being a pre-set one, inclusion in the past results of speech recognition or the linguistic score being not less than a pre-set value. The words so selected are subjected to matching processing.

Speech recognition device and speech recognition method and recording medium utilizing preliminary word selection

A system and method for an automatic set-up of speech recognition engines may include a speech recognizer configured to perform speech recognition procedures to identify input speech data according to one or more operating parameters. A merit manager may be utilized to automatically calculate merit values corresponding to the foregoing recognition procedures. These merit values may incorporate recognition accuracy information, recognition speed information, and a user-specified weighting factor that shifts the relative effect of the recognition accuracy information and the recognition speed information on the merit values. The merit manager may then automatically perform a merit value optimization procedure to select operating parameters that correspond to an optimal one of the merit values.

System and method for an automatic set-up of speech recognition engines

In order to prevent degradation of speech recognition accuracy due to an unknown word, a dictionary database has stored therein a word dictionary in which are stored, in addition to words for the objects of speech recognition, suffixes, which are sound elements and a sound element sequence, which form the unknown word, for classifying the unknown word by the part of speech thereof. Based on such a word dictionary, a matching section connects the acoustic models of an sound model database, and calculates the score using the series of features output by a feature extraction section on the basis of the connected acoustic model. Then, the matching section selects a series of the words, which represents the speech recognition result, on the basis of the score.

Speech recognition with score calculation

The present invention provides a speech recognition apparatus having high speech recognition performance and capable of performing speech recognition in a highly efficient manner. A matching unitcalculates the scores of words selected by a preliminary word selectorand determines a candidate for a speech recognition result on the basis of the calculated scores. A control unitproduces word connection relationships among words included in a word series employed as a candidate for the speech recognition result and stores them into a word connection information storage unit. A reevaluation unitcorrects the word connection relationships one by one. On the basis of the corrected word connection relationships, the control unitdetermines the speech recognition result. A word connection managing unitlimits times allowed for a boundary between words represented by the word connection relationships to be located thereat. A word connection managing unitlimits start times of words preliminarily selected by the preliminary word selector. The present invention can be applied to an interactive system that recognizes an input speech and responds to the speech recognition result.

Speech recognition apparatus

The present invention relates to a voice recognition apparatus capable of easily registering a word which has not been registered. The registering of an unregistered word into a dictionary can be easily performed without causing a significant increase in the size of the dictionary. The clustering unit detects a cluster (detected cluster) to which a new unregistered word is to be added as a new member, from existing clusters obtained by clustering unregistered words. The unregistered word is added as a new member to the detected cluster, and the cluster is divided depending on the members of the cluster such that unregistered words which are acoustically similar to each other belong to the same cluster. The maintenance unit updates the word dictionary on the basis of the result of the clustering. The present invention may be applied to a robot including a voice recognition apparatus.

Sound processing registering a word in a dictionary

Method for recognizing speech includes receiving a speech phrase, generating a signal being representative to the speech phrase, pre-processing and storing the signal with respect to a determined set of rules, generating from the pre-processed signal at least one series of hypothesis speech elements, and determining at least one series of words being most probable to correspond to the speech phrase by applying a predefined language model to at least said series of hypothesis speech elements. The determination of the series of words includes determining at least one sub-word, word, or a combination of words most probably being contained as a seed sub-phrase in the received speech phrase. The determination continues with determining words or combinations of words that are consistent with the seed sub-phrase as at least a first successive sub-phrase, which is contained in the received speech phrase, by using and evaluating additional and paired and/or higher order information between the sub-phrases, thereby decreasing the burden of searching.

Method for recognizing speech

The present invention relates to a speech recognition apparatus for recognizing speeches of a plurality of users with high accuracy. An adapting unitdetects a best transformation function for adapting an input speech to an acoustic model from at least one transformation function based on the transformation results which are obtained by transforming the input speech by at least one transformation function stored in a storing unitand allocates the input speech to the best transformation function. Further, the adapting unitupdates the transformation function to which the new input speech is allocated by all the input speeches allocated to the transformation function. A selecting unitselects the transformation function used for transforming the input speech from at least one transformation function stored in the storing unitA transforming unittransforms the input speech by the selected transformation function. A matching unitperforms matching processing in which the speech obtained by transforming the input speech matches the acoustic model. The present invention can be applied to speech recognition apparatuses.

Speech recognition apparatus and method adapting best transformation function to transform one of the input speech and acoustic model

A preliminary word-selecting section selects one or more words following words which have been obtained in a word string serving as a candidate for a result of speech recognition; and a matching section calculates acoustic or linguistic scores for the selected words, and forms a word string serving as a candidate for a result of speech recognition according to the scores. A control section generates word-connection relationships between words in the word string serving as a candidate for a result of speech recognition, sends them to a word-connection-information storage section, and stores them in it. A re-evaluation section corrects the word-connection relationships stored in the word-connection-information storage sectionand the control section determines a word string serving as the result of speech recognition according to the corrected word-connection relationships.

Speech recognition apparatus, speech recognition method, and storage medium

An extended-word selecting section calculates a score for a phoneme string formed of one more phonemes, corresponding to a user's speech, and searches a large-vocabulary-dictionary for a word having one or more phonemes equal to or similar to those of a phoneme string having a score equal to or higher than a predetermined value. A matching section calculates scores for the word searched for by the extended-word selecting section in addition to a word preliminary word-selecting section. A control section determines a word string as the result of recognition of the speech uttered by the user.

Voice recognition apparatus and method, and recording medium

According to the present invention network devices that can be controlled via a speech unit included in the network can send a device-document describing its functionality and its speech interface to said speech unit. The speech unit combines those documents to a general document that forms the basis to translate recognized user-commands into user-network-commands to control the connected network-devices. A device-document comprises at least the vocabulary and the commands associated therewith for the corresponding device. Furtheron, pronunciation, grammar for word sequences, rules for speech understanding and dialog can be contained in such documents as well as the same information for multiple languages or information for dynamic dialogs in speech understanding. It is possible that one device contains several documents and dynamically sends them to the speech unit in case they are needed. Furtheron, the present invention enables a device to change its functionality dynamically based on changing content, since a network device send its specifications regarding its speech capabilities to the speech unit while the speech unit is in use.

Growing community of inventors

Tokyo, Japan

Helmut Lucke