Itt Corporation

Itt Defense, Inc.

Itt Manufacturing Enterprises, Inc.

Lawrence G Bahler

Alan L Higgins

William Y Huang

Robert E Wohlford

Joe A Naylor

Blakely P Landell

A speech verification process involves comparison of enrollment and test speech data and an improved method of comparing the data is disclosed, wherein segmented frames of speech are analyzed jointly, rather than independently. The enrollment and test speech are both subjected to a feature extraction process to derive fixed-length feature vectors, and the feature vectors are compared, using a linear discriminant analysis and having no dependence upon the order of the words spoken or the speaking rate. The discriminant analysis is made possible, despite a relatively high dimensionality of the feature vectors, by a mathematical procedure provided for finding an eigenvector to simultaneously diagonalize the between-speaker and between-channel covariances of the enrollment and test data.

Method for speech processing involving whole-utterance modeling

An automated system obtains a confirmation of receipt of a notification by the intended recipient by having the recipient speak all or part of the notification. The words spoken by the recipient are determined by a computerized system using an automatic speech recognition algorithm. The computerized system determines whether the words spoken are those of the notification, and if they are, the system accepts the confirmation from the recipient. Optionally, the system additionally applies an automatic speaker recognition algorithm to determine whether the person reciting the notification has similar voice characteristics to the intended recipient based on a previous enrollment of the intended recipient's voice. The system can also record the recipient reciting the notification so that it can later be compared to the intended recipient's voice if the intended recipient repudiates the confirmation.

Automatic confirmation of personal notifications

A system and a method is disclosed for verifying a voice of a user conducting a telephone transaction. The system and method includes a mechanism for prompting the user to speak in a limited vocabulary. A feature extractor converts the limited vocabulary into a plurality of speech frames. A pre-processor is coupled to the feature extractor for processing the plurality of speech frames to produce a plurality of processed frames. The processing includes frame selection, which eliminates each of the plurality of speech frames having an absence of words. A Viterbi decoder is also coupled to said feature extractor for assigning a frame label to each of the plurality of speech frames to produce a plurality of frame labels. The processed frames and frame labels are then combined to produce a voice model, which includes each of the plurality of frame labels that correspond to the number of plurality of processed frames. A mechanism is also provided for comparing the voice model with the claimant's voice model, derived during a previous enrollment session. The voice model also is compared with an alternate voice model set, derived during previous enrollment sessions. The identity claimed is accepted if the voice model matches the claimant's voice model better than the alternative voice model set.

System for voice verification using matched frames

System for voice verification of telephone transactions

A method for recognizing spoken utterances of a speaker is disclosed, the method comprising the steps of providing a database of labeled speech data; providing a prototype of a Hidden Markov Model (HMM) definition to define the characteristics of the HMM; and parameterizing speech utterances according to one of linear prediction parameters or Mel-scale filter bank parameters. The method further includes selecting a frame period for accommodating the parameters and generating HMMs and decoding to specified speech utterances by causing the user to utter predefined training speech utterances for each HMM. The method then statistically computes the generated HMMs with the prototype HMM to provide a set of fully trained HMMs for each utterance indicative of the speaker. The trained HMMs are used for recognizing a speaker by computing Laplacian distances via distance table lookup for utterances of the speaker during the selected frame period; and iteratively decoding node transitions corresponding to the spoken utterances during the selected frame period to determine which predefined utterance is present.

Speaker independent speech recognition method utilizing multiple

A telephone long distance service is provided using speaker verification to determine whether a user is a valid user or an impostor. The user claims an identity by offering some form of identification, typically by entering a calling card number on the phone's touch-tone keypad or by a magnetic strip on the card which is read by the telephone. Unrestricted, extemporaneous speech of a group of customers are digitized, analyzed in accordance with a PCM circuit, and characterized as a non-parametric set of speech feature vectors. The extemporaneous speech of the long distance telephone service user claiming the identity of a service customer via his card number is digitized and analyzed in a like manner. The identity of the user is verified by comparing, either during or after the call, the signals in accordance with an algorithm which compares a reference utterance of a known customer with input utterances from one or more unknown telephone service users, one of which users has claimed the identity of the customer. This comparison results in a decision to accept or reject the hypothesized identity. The identity hypothesis to be tested is thus derived from the calling card of the customer.

System and method for passive voice verification in a telephone network

A speaker recognition apparatus employs a non-parametric baseline algorithm for speaker recognition which characterizes a given speaker's speech patterns by a set of speech feature vectors, and generates match scores which are sums of a ScoreA set equal to the average of the minimum Euclidean squared distance between the unknown speech frame and all reference frames of a given speaker over all frames of the unknown input, and ScoreB set equal to the average of the minimum Euclidean squared distance between each frame of the reference set to all frames of the unknown input. The performance on a queue of talkers is further improved by normalization of reference message match distances. The improved baseline algorithm addresses the co-channel problem of speaker spotting when plural speech signals are intermixed on the same channel by using a union of reference sets for pairs of speakers as the reference set for a co-channel signal, and/or by conversational state modelling.

Automated sorting of voice messages through speaker spotting

Similarity is measured between incoming speech and a plurality of candidate strings of filler and keyword templates to test the hypothesis of a keyword being present against the hypothesis of a keyword not being present in the input speech. As alternatives to a candidate string containing a keyword template, other candidate strings are assembled with filler templates of short speech sounds that may be similar to a keyword. A keyword is 'recognized' only when an optimal candidate string containing the corresponding keyword template is determined to match the input speech more closely than all other candidate strings. A concatenation penalty is added to the partial string score each time a new template is added to a candidate string, in order to bias the score in favor of a candidate string containing a longer, keyword template.

Keyword recognition system and method using template concantenation model

An automatic speech recognition system has a multi-mode training capability using a set of previously stored templates of a limited number of predetermined seed words to train the templates for a vocabulary of words. The training speech samples each includes a vocabulary word juxtaposed with a seed word. An averager module maintains an active average template for each of the word units of the training speech samples including the seed word units, and the active average templates are used to continuously update the seed template set as they are used in the training speech samples. The preferred training procedure employs training phrases each having a vocabulary word embedded between two seed words, and two seed template sets are used in succession, the first being composed of single-digit words, and the second composed of carrier words.

Automatic speech recognition system using seed templates

An automatic speech recognition system employs parallel syntaxes with a first syntax operative to compare keyword templates with incoming speech over a given time interval and with a second syntax in parallel with the first and operative to compare filler templates with incoming speech over the same interval. Based on the best comparisons in each syntax a likelihood probability ratio is computed and compared against a selected threshold for determining whether the speech contains a valid phrase or keyword as compared to an undesirable utterance.

Growing community of inventors

San Diego, CA, United States of America

Lawrence G Bahler