Abstract: An anaphora analyzing apparatus is disclosed for automatically estimating an anaphora referential relation or an antecedent of a noun for use in a natural language sentence. A storage unit stores analyzed results outputted from an analyzer, and an antecedent candidate generator detects a target component required for anaphora analysis in accordance with the current analyzed results and the past analyzed results stored in the storage unit, and generates antecedent candidates corresponding to the target component. Then, a candidate rejecting section rejects unnecessary candidates having no potential for anaphora referential relation among the antecedent candidates by using a predetermined rejecting criterion, and outputs the remaining antecedent candidates.

Abstract: In a speaker normalization processor apparatus, a vocal-tract configuration estimator estimates feature quantities of a vocal-tract configuration showing an anatomical configuration of a vocal tract of each normalization-target speaker, by looking up to a correspondence between vocal-tract configuration parameters and Formant frequencies previously determined based on a vocal tract model of the standard speaker, based on speech waveform data of each normalization-target speaker.

Abstract: In an analogically similar word production apparatus, based on three inputted unit strings, an analogically similar word which is a word analogically similar to inputted unit strings is produced at high speed without using attributes and without any finite state automaton. A pseudo-distance matrix memory stores therein only matrix elements sufficient for computation of limited pseudo distances between two letter strings, out of the elements of two pseudo-distance matrices, and more specifically, matrix elements including diagonal elements are computed by a preprocessing section and then stored in the pseudo-distance matrix memory.

Abstract: There are disclosed an apparatus for calculating a posteriori probabilities of phoneme symbols and a speech recognition apparatus using the apparatus for calculating a posteriori probabilities of phoneme symbols. A feature extracting section extracts speech feature parameters from a speech signal of an uttered speech sentence composed of an inputted character series, and a calculating section calculates a a posteriori probability of a phoneme symbol of the speech signal, by using a bidirectional recurrent neural network. The bidirectional recurrent neural network includes (a) an input layer for receiving the speech feature parameters extracted by the feature extracting means and a plurality of hypothetical phoneme symbol series signals, (b) an intermediate layer of at least one layer having a plurality of units, and (c) an output layer for outputting a a posteriori probability of each phoneme symbol.

Abstract: Provided is a similarity search apparatus for searching data at a higher speed than that of the prior art without limiting the types of letter of a search key. A unit position correspondence memory stores therein a table that expresses the ordinal number among units at which each unit in a search key inputted by means of a keyboard has appeared within the search key. A search section refers to the table stored in the unit position correspondence memory and operates every time units are read out one by one from a database memory including a plurality of units to generate a plurality of status parameters each of which includes a similarity, a position of coincidence and a skip number, which express with what number of units from the top of the search key the units read out from the database have coincided at what degree of similarity, and express how many units in the database have been skipped over subsequently.

Abstract: A speaker clustering apparatus generates HMMs for clusters based on feature quantities of a vocal-tract configuration of speech waveform data, and a speech recognition apparatus provided with the speaker clustering apparatus. In response to the speech waveform data of N speakers, an estimator estimates feature quantities of vocal-tract configurations, with reference to correspondence between vocal-tract configuration parameters and Formant frequencies predetermined based on a predetermined vocal tract model of a standard speaker. Further, a clustering processor calculates speaker-to-speaker distances between the N speakers based on the feature quantities of the vocal-tract configurations of the N speakers as estimated, and clusters the vocal-tract configurations of the N speakers using a clustering algorithm based on calculated speaker-to-speaker distances, thereby generating K clusters.

Abstract: A speech recognition apparatus which includes a speech recognition section for performing a speech recognition process on an uttered speech with reference to a predetermined statistical language model, based on a series of speech signal of the uttered speech sentence composed of a series of input words. The speech recognition section calculates a functional value of a predetermined erroneous sentence judging function with respect to speech recognition candidates, where the erroneous sentence judging representing a degree of unsuitability for the speech recognition candidates. When the calculated functional value exceeds a predetermined threshold value, the speech recognition section performs the speech recognition process by eliminating a speech recognition candidate corresponding to a calculated functional value.

Abstract: There is provided a speaker-independent model generation apparatus and a speech recognition apparatus which require a processing unit to have less memory capacity and which allow its computation time to be reduced, as compared with a conventional counterpart. A single Gaussian HMM is generated with a Baum-Welch training algorithm based on spoken speech data from a plurality of specific speakers. A state having a maximum increase in likelihood as a result of splitting one state in contextual or temporal domains is searched. Then, the state having a maximum increase in likelihood is split in a contextual or temporal domain corresponding to the maximum increase in likelihood. Thereafter, a single Gaussian HMM is generated with the Baum-Welch training algorithm, and these steps are iterated until the states within the single Gaussian HMM can no longer be split or until a predetermined number of splits is reached. Thus, a speaker-independent HMM is generated.

Abstract: In a signal pattern recognition apparatus, a plurality of feature transformation sections respectively transform an inputted signal pattern into vectors in a plurality of feature spaces corresponding respectively to predetermined classes using a predetermined transformation parameter corresponding to each of the classes so as to emphasize a feature of each of the classes, and a plurality of discriminant function sections respectively calculates a value of a discriminant function using a predetermined discriminant function representing a similarity measure of each of the classes for the transformed vectors in the plurality of feature spaces.