Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating speech. One variation of the method is from a server side, and another variation of the method is from a client side. The server side method, as implemented by a network-based automatic speech processing system, includes first receiving, from a network client independent of knowledge of internal operations of the system, a request to generate a text-to-speech voice. The request can include speech samples, transcriptions of the speech samples, and metadata describing the speech samples. The system extracts sound units from the speech samples based on the transcriptions and generates an interactive demonstration of the text-to-speech voice based on the sound units, the transcriptions, and the metadata, wherein the interactive demonstration hides a back end processing implementation from the network client. The system provides access to the interactive demonstration to the network client.

Abstract: A method and system are disclosed that automatically segment speech to generate a speech inventory. The method includes initializing a Hidden Markov Model (HMM) using seed input data, performing a segmentation of the HMM into speech units to generate phone labels, correcting the segmentation of the speech units. Correcting the segmentation of the speech units includes re-estimating the HMM based on a current version of the phone labels, embedded re-estimating of the HMM, and updating the current version of the phone labels using spectral boundary correction. The system includes modules configured to control a processor to perform steps of the method.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for detecting and correcting abnormal stress patterns in unit-selection speech synthesis. A system practicing the method detects incorrect stress patterns in selected acoustic units representing speech to be synthesized, and corrects the incorrect stress patterns in the selected acoustic units to yield corrected stress patterns. The system can further synthesize speech based on the corrected stress patterns. In one aspect, the system also classifies the incorrect stress patterns using a machine learning algorithm such as a classification and regression tree, adaptive boosting, support vector machine, and maximum entropy. In this way a text-to-speech unit selection speech synthesizer can produce more natural sounding speech with suitable stress patterns regardless of the stress of units in a unit selection database.

Abstract: Systems and methods are provided for recognizing speech in a spoken dialogue system. The method includes receiving input speech having a pre-vocalic consonant or a post-vocalic consonant, generating at least one output lattice that calculates a first score by comparing the input speech to a training model to provide a result and distinguishing between the pre-vocalic consonant and the post-vocalic consonant in the input speech. A second score is calculated by measuring a similarity between the pre-vocalic consonant or the post vocalic consonant in the input speech and the first score. At least one category is determined for the pre-vocalic match or mismatch or the post-vocalic match or mismatch by using the second score and the results of the an automated speech recognition (ASR) system are refined by using the at least one category for the pre-vocalic match or mismatch or the post-vocalic match or mismatch.

Abstract: Disclosed are systems, methods and computer readable media for training acoustic models for an automatic speech recognition systems (ASR) system. The method includes receiving a speech signal, defining at least one syllable boundary position in the received speech signal, based on the at least one syllable boundary position, generating for each consonant in a consonant phoneme inventory a pre-vocalic position label and a post-vocalic position label to expand the consonant phoneme inventory, reformulating a lexicon to reflect an expanded consonant phoneme inventory, and training a language model for an automated speech recognition (ASR) system based on the reformulated lexicon.

Abstract: A data stream is filtered to produce a filtered data stream. The data stream is analyzed based on an acoustic parameter to determine whether a predetermined condition is satisfied. At least one extraneous portion of the data stream, in which the predetermined condition is satisfied, is determined. Thereafter, the at least one extraneous portion is deleted from the data stream to produce the filtered data stream.

Abstract: A method, apparatus, and computer-readable medium for editing a data stream based on a corpus are provided. The data stream includes stream words. A sequence includes a predetermined number of sequential words of the stream words. The method, apparatus, and computer-readable medium determine whether the sequence exists in the corpus at least at a predetermined minimum frequency. When the sequence exists in the corpus at least at the predetermined minimum frequency, the sequence is edited in the data stream.

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for unit selection synthesis. The method causes a computing device to add a supplemental phoneset to a speech synthesizer front end having an existing phoneset, modify a unit preselection process based on the supplemental phoneset, preselect units from the supplemental phoneset and the existing phoneset based on the modified unit preselection process, and generate speech based on the preselected units. The supplemental phoneset can be a variation of the existing phoneset, can include a word boundary feature, can include a cluster feature where initial consonant clusters and some word boundaries are marked with diacritics, can include a function word feature which marks units as originating from a function word or a content word, and/or can include a pre-vocalic or post-vocalic feature. The speech synthesizer front end can incorporates the supplemental phoneset as an extra feature.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for captioning a media presentation. The method includes receiving automatic speech recognition (ASR) output from a media presentation and a transcription of the media presentation. The method includes selecting via a processor a pair of anchor words in the media presentation based on the ASR output and transcription and generating captions by aligning the transcription with the ASR output between the selected pair of anchor words. The transcription can be human-generated. Selecting pairs of anchor words can be based on a similarity threshold between the ASR output and the transcription. In one variation, commonly used words on a stop list are ineligible as anchor words. The method includes outputting the media presentation with the generated captions. The presentation can be a recording of a live event.

Abstract: A method of detecting pre-determined phrases to determine compliance quality is provided. The method includes determining whether at least one of an event or a precursor event has occurred based on a comparison between pre-determined phrases and a communication between a sender and a recipient in a communications network, and rating the recipient based on the presence of the pre-determined phrases associated with the event or the presence of the pre-determined phrases associated with the precursor event in the communication.

Abstract: Predicting a score related to a communication sent by a sender over a communications network to a first agent servicing the communication includes obtaining a regression result for an objective function by encoding features extracted from the communication. The encoded features are applied to a regression model for the objective function. The regression result is output to a network component in the communications network. The regression model is determined prior to or concurrently with receiving the communication from the sender.

Abstract: Provided are a system and method for providing contents service. A service storing apparatus stores service providing information and service request information. A service requesting apparatus composes a service search inquiry according to a contents service request, receives the inquiry result, and calls a corresponding service based on the received result to provide a corresponding contents service. A service relaying apparatus searches related service providing information from the service storing apparatus to provide information necessary for calling the service when the service search inquiry is received. A service providing apparatus provides service proxy information of a content service and provides a corresponding contents service when a service is called by a service requesting apparatus.

Abstract: A method of correlating received communication data with operational communication characteristics is provided. The method includes receiving audible input from a source in a communication over a communications network, recording the received audible input, and transcribing the recorded audible input into a transcript. The method further includes outputting the transcript, specifying features of the transcript to be analyzed, specifying and recording operational communication characteristics particular to the communication, analyzing the transcript for the specified features to identify patterns associated with the audible input, computing statistical correlations of the identified patterns with the operational communication characteristics, and outputting results of the computed statistical correlations on a user interface.

Abstract: A method and system are disclosed that automatically segment speech to generate a speech inventory. The method includes initializing a Hidden Markov Model (HMM) using seed input data, performing a segmentation of the HMM into speech units to generate phone labels, correcting the segmentation of the speech units. Correcting the segmentation of the speech units includes re-estimating the HMM based on a current version of the phone labels, embedded re-estimating of the HMM, and updating the current version of the phone labels using spectral boundary correction. The system includes modules configured to control a processor to perform steps of the method.

Abstract: Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

Abstract: Provided is a path-token-based web service caching method including determining whether or not stored cache data exists when a web service call request exists, and when the cache data does not exist, creating a predetermined path-token set and a predetermined tag data set based on a message schema of Web Services Description Language (WSDL), and creating a request Simple Object Access Protocol (SOAP) message, creating a request SOAP message template by using a path-token for the created request SOAP message, and calling the web service, and creating cache data including the tag data set, input values set, the request SOAP message template, the request SOAP message, and SOAP binding information. Accordingly, the method can solve the problems of a conventional web service caching method whereby the method can not cope with change in the number of inputs, and an exact input position is not searched for when an input value is changed.

Abstract: Disclosed are systems, methods and computer readable media for training acoustic models for an automatic speech recognition systems (ASR) system. The method includes receiving a speech signal, defining at least one syllable boundary position in the received speech signal, based on the at least one syllable boundary position, generating for each consonant in a consonant phoneme inventory a pre-vocalic position label and a post-vocalic position label to expand the consonant phoneme inventory, reformulating a lexicon to reflect an expanded consonant phoneme inventory, and training a language model for an automated speech recognition (ASR) system based on the reformulated lexicon.

Abstract: A system and method are disclosed for synthesizing speech based on a selected speech act. A method includes modifying synthesized speech of a spoken dialogue system, by (1) receiving a user utterance, (2) analyzing the user utterance to determine an appropriate speech act, and (3) generating a response of a type associated with the appropriate speech act, wherein in linguistic variables in the response are selected, based on the appropriate speech act.

Abstract: Disclosed are systems and methods for recognizing speech in a spoken dialogue system.

Abstract: Provided are a system and method for providing contents service. A service storing apparatus stores service providing information and service request information. A service requesting apparatus composes a service search inquiry according to a contents service request, receives the inquiry result, and calls a corresponding service based on the received result to provide a corresponding contents service. A service relaying apparatus searches related service providing information from the service storing apparatus to provide information necessary for calling the service when the service search inquiry is received. A service providing apparatus provides service proxy information of a content service and provides a corresponding contents service when a service is called by a service requesting apparatus.