Abstract: A system and methods are provided for conducting an interactive dialog via a speech-based user interface. The system includes an auditory prompt module for generating a sequence of goal-directed auditory prompts based upon a pre-determined user-oriented task, and an error recovery module for responding to a communication error by initiating an error recovery based upon a user response to the sequence of goal-directed auditory prompts. The error recovery includes providing at least one error-recovery prompt selected from a hierarchy of error-recovery prompts, the selection based upon a hierarchy of communication error types.

Abstract: There is described a number of encoders for encoding a data signal within an audio signal. In some of the encoders, the audio signal is separated into a tonal part and a residual part, and the data signal is shaped based on the residual part. In other encoders, the data signal is separated into a tonal part and a residual part, and the data signal is combined with the audio signal independence upon the residual part. In other encoders, the rate at which the data is encoded within the audio signal is varied in dependence upon the audio signal. There are also described various decoders associated with the described encoders.

Abstract: A method for discriminatively training acoustic models is provided for automated speaker verification (SV) and speech (or utterance) verification (UV) systems.

Abstract: A voice recognition estimating apparatus for a voice recognition apparatus, including a voice data property generator that generates properties of voice data used to determine, based on an estimation item, a feature of synthetic voice data. The estimation item is used to estimate a performance of the voice recognition apparatus. The voice data property generator includes an acquisition unit that acquires vocabulary data and unnecessary word data as the estimation item. The unnecessary word data indicates an unnecessary word inserted in the vocabulary data and an insertion position of the unnecessary word. The voice data property generator also includes a generator that generates the properties of the voice data. The properties of the voice data include selected voice quality data items, the vocabulary data and the unnecessary word data.

Abstract: Relatively powerful hand-held computing devices, Digital Signal Processors, Audio signal processing technology, voice recognition technology, expert systems, Hidden Markov Models, and/or neural networks are employed in a device capable of real-time automated species identification by listening to bird vocalizations in the field, analyzing their waveforms, and comparing these waveforms against known reference samples.

Abstract: An information display control apparatus includes: an example sentence storing unit for storing example sentences each including words; a word inputting unit for inputting a word; a list display control unit for controlling a search for example sentences each including the inputted word among the stored example sentences, and a display of a list of the searched example sentences; an addition word selecting unit for selecting an addition word among the words in the example sentences of which the list is displayed by the list display control unit, while the list of the example sentences each including the inputted word is displayed under control of the list display control unit; and a list display update control unit for controlling a search for example sentences each including the selected addition word and the inputted word, among the stored example sentences, and an update of the display of the list.

Abstract: A voice discriminating tag for making a reception voice and a transmission voice distinguishable is added to the voice inputted into a cell phone. Further, a volume discriminating tag is added based on a detection result of a volume detector. A CPU converts the voice into character data and image data on the basis of the voice discriminating tag and the volume discriminating tag, referring to various files stored in file devices. The converted data is outputted to a display panel on which the character data corresponding to the transmission voice and the character data corresponding to the reception voice are shown in time series so as to have different colors. The character data is shown in a literal type corresponding to a volume level.

Abstract: Emotion recognition is performed by extracting a set comprising at least one feature derived from a signal, and processing the set of extracted feature(s) to detect an emotion therefrom. The voice signal is low pass filtered prior to extracting therefrom at least one feature of the set. The cut-off frequency for the low pass filtering is typically centered around 250 Hz. The features are e.g. statistical quantities extracted from sampling a signal of the intensity or pitch of the voice signal.

Abstract: A sound processor including a microphone (1), a pre-amplifier (2), a bank of N parallel filters (3), means for detecting short-duration transitions in the envelope signal of each filter channel, and means for applying gain to the outputs of these filter channels in which the gain is related to a function of the second-order derivative of the slow-varying envelope signal in each filter channel, to assist in perception of low-intensity sort-duration speech features in said signal.

Abstract: National language support for an application is provided by recording translations of a text string in corresponding different languages in a single property file so as to allow display of the translations in the property file. One of the translations of the text string recorded in the property file is selected for use by an application based on a locale associated with the execution of the application and the selected one of the translations is used in the execution of the application.

Abstract: A system and method for creating user voice profiles enables a user to create a single user voice profile that is compatible with one or more voice servers. Such a system includes a training server that receives audio information from a client associated with a user and stores the audio information and corresponding textual information. The system further includes a training server adaptor. The training server adaptor is configured to receive a voice profile format and a communication protocol corresponding to one of the plurality of voice servers, convert the audio information and corresponding textual information into a format compatible with the voice profile format and communication protocol corresponding to the one of the plurality of voice servers, and provide the converted audio information and corresponding textual information to the one of the plurality of voice servers.

Abstract: A method for adding words to an online dictionary used for spellchecking is described. A spellchecker module compares words of an electronic document with words in the online dictionary and identifies a word in the electronic document that is missing from the dictionary. After a user indicates a desire to add the missing word to the dictionary, the spellchecker module determines at least one related-word form of the missing word. The related-word forms depend upon the part of speech of the missing word. The spellchecker can prompt the user to identify the part of speech and then to verify each determined related-word form. The spellchecker concurrently adds the missing word and at least one related-word form of the missing word to the online dictionary in a single ‘add-to-dictionary’ operation.

Abstract: The present invention provides a diagnostic device that presents, to a patient, a Noise-Vocoded Speech Sound signal that is obtained by dividing at least one portion of a sound signal into a single or a plurality of frequency band signals and subjecting the frequency band signals to noise, and analyzing the content of a response recognized by the patient and the presented stimulus to diagnose a disease of the patient based on the analysis results, so that diagnosis including determining the disease of the patient and estimating a damaged site can be performed.

Abstract: An interactive information providing apparatus is provided with: an output component that provides an information requesting output for requesting a user for information; an input component that receives from the user input information to the information requesting output; and an interaction controller component that controls the output component and the input component according to a scenario, to carry on a dialogue with the user. In the apparatus, the interaction controller component changes a level at which the output component requests a user for information, according to an importance parameter associated with the scenario.

Abstract: An information display control apparatus capable of searching for an example sentence suitable for words input as a search phrase and displaying the example sentence. The information display control apparatus has: an example sentence storage means for storing an example sentence and an entry word thereof; an example sentence and word storage means for storing a word and the example including the word; an input means for inputting a plurality of words; an extraction means for extracting the example sentence including the plurality of words among the example sentence stored in the example sentence and word storage means; and a display control means for performing control of extracting the example sentence stored with the entry word which corresponds to any word or an altered form of any word among the plurality of words among the example sentence extracted by the extraction means, and displaying the extracted example sentence.

Abstract: Speech recognition is performed by matching between a characteristic quantity of an inputted speech and a composite HMM obtained by synthesizing a speech HMM (hidden Markov model) and a noise HMM for each speech frame of the inputted speech by use of the composite HMM.

Abstract: Methods and systems for syntactically indexing and searching data sets to achieve more accurate search results and for indexing and searching data sets using entity tags alone or in combination therewith are provided. Example embodiments provide a Syntactic Query Engine (“SQE”) that parses, indexes, and stores a data set, as well as processes natural language queries subsequently submitted against the data set. The SQE comprises a Query Preprocessor, a Data Set Preprocessor, a Query Builder, a Data Set Indexer, an Enhanced Natural Language Parser (“ENLP”), a data set repository, and, in some embodiments, a user interface. After preprocessing the data set, the SQE parses the data set according to a variety of levels of parsing and determines as appropriate the entity tags and syntactic and grammatical roles of each term to generate enhanced data representations for each object in the data set. The SQE indexes and stores these enhanced data representations in the data set repository.

Abstract: A method and device for performing some preprocessing on voice transmissions depending upon the intended destination of the transmission. The device includes a receiving component configured to receive a voice signal from a source over a network. The device also includes a processing component configured to determine a destination address associated with the received signal, determine a signal processing algorithm from a plurality of signal processing algorithms based on the determined address, and process the voice signal according to the specified algorithm. The device further includes a delivery component configured to send the processed signal to the associated address.

Abstract: A system and method for classifying a voice signal to one of a set of predefined categories, based upon a statistical analysis of features extracted from the voice signal. The system includes an acoustic processor and a classifier. The acoustic processor extracts features that are characteristic of the voice signal and generates feature vectors using the extracted spectral features. The classifier uses the feature vectors to compute the probability that the voice signal belongs to each of the predefined categories and classifies the voice signal to a predefined category that is associated with the highest probability.

Abstract: A phonetic vocabulary for a speech recognition system is adapted to a particular speaker's pronunciation. A speaker can be attributed specific pronunciation styles, which can be identified from specific pronunciation examples. Consequently, a phonetic vocabulary can be reduced in size, which can improve recognition accuracy and recognition speed.