U.S. Philips Corporation

Nuance Communications, Inc.

Peter Beyerlein

Meinhard D Ullrich

Eric Thelen

Reinhold Hab-Umbach

Xavier Aubert

Methods and apparatus for identifying a user group in connection with user group-based speech recognition. An exemplary method comprises receiving, from a user, a user group identifier that identifies a user group to which the user was previously assigned based on training data. The user group comprises a plurality of individuals including the user. The method further comprises using the user group identifier, identifying a pattern processing data set corresponding to the user group, and receiving speech input from the user to be recognized using the pattern processing data set.

Pattern processing system specific to a user group

A method for recognizing a pattern that comprises a set of physical stimuli, said method comprising the steps of:

Method of determining model-specific factors for pattern recognition, in particular for speech patterns

For the recognition of spoken text it is necessary that the words to be recognized are available in acoustically modeled form, i.e. in the form of a sequence of reference values. These reference values are determined from a known, spoken text during a training phase, in that from this text there are derived characteristic values at regular intervals, as during the recognition, which characteristic values are arranged according to triphones so as to form groups or so-called clusters. These groups constitute the basis for the reference values. In the case of a recognition system involving a very large vocabulary, however, not all triphones will occur during the training phase, unless the text is prohibitively long. In order to enable the reference values to be determined also for words containing triphones which have not occurred, such a triphone must be associated with an available group. To this end, all groups are examined so as to determine whether they have the same central phoneme in interrelationship with either the left-hand or the right-hand phoneme as the triphone to be associated. The group for which this is most often the case is selected as the associated group. The vast majority of words can thus be modeled on the basis of triphones. Modifications of this rule are described for words containing triphones which cannot be directly associated in this manner.

Method of determining an acoustic model for a word

A system and method are used for recognising a time-sequential input pattern (20), which is derived from a continual physical quantity, such as speech. The system has input means (30), which accesses the physical quantity and therefrom generates a plurality of input observation vectors. The input observation vectors represent the input pattern. A reference pattern database (40) is used for storing a plurality of reference patterns. Each reference pattern includes a sequence of reference units, where each reference unit is represented by at least one associated reference vector .mu..sub.a in a set {.mu..sub.a } of reference vectors. A localizer (50) is used for locating among the reference patterns stored in the reference pattern database (40), a recognised reference pattern, which corresponds to the input pattern. The locating includes selecting a subset {.mu..sub.s } of reference vectors from said set {.mu..sub.a } for each input observation vector o by calculating a measure of dissimilarity between the input observation vector o and each reference vector of the set {.mu..sub.a }. A number of reference vectors .mu..sub.a, whose measures of dissimilarity with said input observation vector o are the smallest, are used as the subset {.mu..sub.s } of reference vectors. The reference vectors of the subset {.mu..sub.s } are used to calculate for each reference pattern, a pattern similarity score. The recognised pattern is one of the reference patterns for which an optimum of the pattern similarity scores is calculated. Output means (70) are used for outputting the recognised pattern.

Method and system for pattern recognition based on dynamically

For speech recognition a new word is represented as based on a stored inventory of models of sub-word units. First a plurality of utterances are presented that all should conform to the word. For building a word model from the utterances, these are represented by a sequence of feature vectors. First, the utterances are used to train a whole-word model that is independent of the models of the sub-word units. The length of the whole-word model equals the average length of the utterances. Next, a sequence of Markov states and associated probability densities of acoustic events of the whole-word model is interpreted as a reference template represented by a string of averaged feature vectors. Finally, the string is recognized by matching to models in the inventory and storing a recognition result as a model of the utterances.

Growing community of inventors

Aachen, Germany

Peter Beyerlein