Abstract: A data collection system is based on a general set of dialogue acts which are derived from a database schema. Crowd workers perform two types of tasks: (i) identification of sensical dialogue paths and (ii) performing context-dependent paraphrasing of these dialogue paths into real dialogues. The end output of the system is a set of training examples of real dialogues which have been annotated with their logical forms. This data can be used to train all three components of the dialogue system: (i) the semantic parser for understanding context-dependent utterances, (ii) the dialogue policy for generating new dialogue acts given the current state, and (iii) the generation system for both deciding what to say and how to render it in natural language.

Abstract: In one aspect, a method of processing a voice signal to extract information to facilitate training a speech synthesis model is provided. The method comprises acts of detecting a plurality of candidate features in the voice signal, performing at least one comparison between one or more combinations of the plurality of candidate features and the voice signal, and selecting a set of features from the plurality of candidate features based, at least in part, on the at least one comparison. In another aspect, the method is performed by executing a program encoded on a computer readable medium. In another aspect, a speech synthesis model is provided by, at least in part, performing the method.

Abstract: In one aspect, a method of processing a voice signal to extract information to facilitate training a speech synthesis model is provided. The method comprises acts of detecting a plurality of candidate features in the voice signal, performing at least one comparison between one or more combinations of the plurality of candidate features and the voice signal, and selecting a set of features from the plurality of candidate features based, at least in part, on the at least one comparison. In another aspect, the method is performed by executing a program encoded on a computer readable medium. In another aspect, a speech synthesis model is provided by, at least in part, performing the method.

Abstract: Speech errors for a learner of a language (e.g., an English language learner) are identified automatically based on aggregated characteristics of that learner's speech.

Abstract: In one aspect, a method of processing a voice signal to extract information to facilitate training a speech synthesis model is provided. The method comprises acts of detecting a plurality of candidate features in the voice signal, performing at least one comparison between one or more combinations of the plurality of candidate features and the voice signal, and selecting a set of features from the plurality of candidate features based, at least in part, on the at least one comparison. In another aspect, the method is performed by executing a program encoded on a computer readable medium. In another aspect, a speech synthesis model is provided by, at least in part, performing the method.

Abstract: A method of extracting a subset of speech units from a larger set of speech units for use by a speech synthesizer in synthesizing speech, wherein the speech units are stored in a compressed encoded representation that was generated by a codec, the method comprising: selecting members of the subset of speech units based on an overall cost associated with using the speech synthesizer to synthesize a test set of speech, wherein the overall cost includes at least one error introduced by using the codec to decode the stored representations of the speech units; and storing the selected subset of speech units on a speech-enabled device.

Abstract: According to certain aspects of the invention a mobile voice communication device includes a wireless transceiver circuit for transmitting and receiving auditory information and data, a processor, and a memory storing executable instructions which when executed on the processor causes the mobile voice communication device to provide a selectable personality associated with a user interface to a user of the mobile voice communication device. The executable instructions include implementing on the device a user interface that employs the different user prompts having the selectable personality, wherein each selectable personality of the different user prompts is defined and mapped to data stored in at least one database in the mobile voice communication device. The mobile voice communication device may include a decoder that recognizes a spoken user input and provides a corresponding recognized word, and a speech synthesizer that synthesizes a word corresponding to the recognized word.

Abstract: Statistics are measured from an initial portion of a speech utterance. Feature normalization parameters are estimated based on the measured statistics and a statistically derived mapping relating measured statistics and feature normalization parameters.

Abstract: A method of operating a mobile communication device having a set of one or more applications, each with its own associated user-configurable customization, the method comprising detecting whether the user-configurable customization of any of the applications has changed since an earlier time, and for all applications for which the user-configurable customization has changed since said earlier time, wirelessly transmitting those changes to a remote server. The method further comprises maintaining a set of flags indicating whether changes have occurred to the user-configurable customization, wherein detecting whether the user-configurable customization of any of the applications has changed since said earlier time includes reading the set of flags. The remote server is one of a carrier server and a third party provider server.

Abstract: A method of generating an alternative pronunciation for a word or phrase, given an initial pronunciation and a spoken example of the word or phrase, includes providing the initial pronunciation of the word or phrase, and generating the alternative pronunciation by searching a neighborhood of pronunciations about the initial pronunciation via a constrained hypothesis, wherein the neighborhood includes pronunciations that differ from the initial pronunciation by at most one phoneme. The method further includes selecting a highest scoring pronunciation within the neighborhood of pronunciations.

Abstract: A method of operating a device that includes speech recognition capabilities includes implementing on a device a plurality of user interfaces, wherein at least one said user interfaces is a voice interface. The method also includes launching a first application, and as part of launching the first application, launching a second application, the second application optionally presenting to a user at least one query using the voice interface and populating an address field in the first application in response to the query using the speech recognition capabilities. The second application is launched either simultaneously or subsequent to the launching of the first application. Populating the address field comprises accessing address information from a plurality of databases resident in the device.

Abstract: A method of constructing a list of alternate transcripts from a recognized transcript includes generating a list of close call records, matching partial sub-histories from the recognized transcript with one of the history pairs stored in each of the records, and substituting the other of the history pairs for the partial sub-history of the recognized transcript. A close call record is generated each time a pair of partial hypotheses attempt to seed a common word. Each close call record includes history information and scoring information associated with a particular pair of partial hypotheses seeding a common word. Alternate transcripts are constructed by substituting close call histories for partial histories of the recognized transcripts, and also by substituting close call histories for partial histories of other alternate transcript.

Abstract: The invention provides a method of deriving generally improved statistical acoustic model of a first class of speech sounds, given a limited amount of sampling data from that first class. This is done by combining a first statistic calculated from samples of that class of speech sounds with a corresponding second statistic calculated from samples of a second, broader, class of speech sounds. Preferably the second statistic is calculated from many more samples than the first statistic, so it has less sampling error that the first statistic, and preferably the second class is a super-set of the first class, so that the second statistic will provide information about the first class. In one embodiment, the invention combines statistics from the models of a plurality of first classes of speech sounds to reduce the sampling error of such statistics and thus improve the accuracy with which such models can be divided into groups of similar models.

Abstract: A method is provided for deriving acoustic word representations for use in speech recognition. Initial word models are created, each formed of a sequence of acoustic sub-models. The acoustic sub-models from a plurality of word models are clustered, so as to group acoustically similar sub-models from different words, using, for example, the Kullback-Leibler information as a metric of similarity. Then each word is represented by cluster spelling representing the clusters into which its acoustic sub-models were placed by the clustering. Speech recognition is performed by comparing sequences of frames from speech to be recognized against sequences of acoustic models associated with the clusters of the cluster spelling of individual word models.

Abstract: A first speech recognition method receives an acoustic description of an utterance to be recognized and scores a portion of that description against each of a plurality of cluster models representing similar sounds from different words. The resulting score for each cluster is used to calculate a word score for each word represented by that cluster. Preferably these word scores are used to prefilter vocabulary words, and the description of the utterance includes a succession of acoustic decriptions which are compared by linear time alignment against a succession of acoustic models. A second speech recognition method is also provided which matches an acoustic model with each of a succession of acoustic descriptions of an utterance to be recognized. Each of these models has a probability score for each vocabulary word. The probability scores for each word associated with the matching acoustic models are combined to form a total score for that word.

Abstract: A method determines if a portion of speech corresponds to a speech pattern by time aligning both the speech and a plurality of speech pattern models against a common time-aligning model. This compensates for speech variation between the speech and the pattern models. The method then compares the resulting time-aligned speech model against the resulting time-aligned pattern models to determine which of the patterns most probably corresponds to the speech. Preferably there are a plurality of time-aligning models, each representing a group of somewhat similar sound sequences which occur in different words. Each of these time-aligning models is scored for similarity against a portion of speech, and the time-aligned speech model and time-aligned pattern models produced by time alignment with the best scoring time-aligning model are compared to determine the likelihood that each speech pattern corresponds to the portion of speech. This is performed for each successive portion of speech.

Abstract: A method of speech analysis calculates one or more difference parameters for each of a sequence of acoustic frames, where each difference parameter is a function of the difference between an acoustic parameter in one frame and an acoustic parameter in a nearby frame. The method is used in speech recognition which compares the difference parameters of each frame against acoustic models representing speech units, where each speech-unit model has a model of the difference parameters associated with the frames of its speech unit. The difference parameters can be slope parameters or energy difference parameters. Slope parameters are derived by finding the difference between the energy of a given spectral parameter of a given frame and the energy, in a nearby frame, of a spectral parameter associated with a different frequency band. The resulting parameter indicates the extent to which the frequency of energy in the part of the spectrum represented by the given parameter is going up or going down.