Abstract: A machine translation method for translating source text from a first language to target text in a second language includes receiving the source text in the first language and accessing a library of bi-fragments, each of the bi-fragments including a text fragment from the first language and a text fragment from the second language, at least some of the bi-fragments comprising non-contiguous bi-fragments in which at least one of the text fragment from the first language and the text fragment from the second language comprises a non-contiguous fragment.

Abstract: A tailored speaker-independent voice recognition system has a speech recognition dictionary (360) with at least one word (371). That word (371) has at least two transcriptions (373), each transcription (373) having a probability factor (375) and an indicator (377) of whether the transcription is active. When a speech utterance is received (510), the voice recognition system determines (520, 530) the word signified by the speech utterance, evaluates (540) the speech utterance against the transcriptions of the correct word, updates (550) the probability factors for each transcription, and inactivates (570) any transcription that has an updated probability factor that is less than a threshold.

Abstract: A method and system for dynamically assigning weights to the subset of commands in a natural language dialog system based on prior context of the user's interaction with the system. The search space of the translation process may be reduced when some context information is available. A user presents input to the natural language understanding system. The system translates the user input into a formal command and calculates a weight value for a next set of formal commands based on the formal command. The command weights may then be dynamically boosted for the next set of formal commands before executing the formal command. The exemplary aspects of the present invention reduce the time needed to complete a task since the search space of the translation process may be reduced if context information is available and improve the accuracy of the process by using knowledge that users regularly use repeating patterns for repeating tasks.

Abstract: Methods and systems for extending keyword searching techniques to syntactically and semantically annotated data are provided. Example embodiments provide a Syntactic Query Engine (“SQE”) that parses, indexes, and stores a data set as an enhanced document index with document terms as well as information pertaining to the grammatical roles of the terms and ontological and other semantic information. In one embodiment, the enhanced document index is a form of term-clause index, that indexes terms and syntactic and semantic annotations at the clause level. The enhanced document index permits the use of a traditional keyword search engine to process relationship queries as well as to process standard document level keyword searches. In one embodiment, the SQE comprises a Query Processor, a Data Set Preprocessor, a Keyword Search Engine, a Data Set Indexer, an Enhanced Natural Language Parser (“ENLP”), a data set repository, and, in some embodiments, a user interface or an application programming interface.

Abstract: A hands-free circuit (10) and method produces audio information (90) corresponding to voice tag information (60) stored either in the hands-free circuit (10) or in a wireless device (320). The hands-free circuit includes a wireless local area network (WLAN) transceiver (20), memory (40) and a speech processor (30). For example, the wireless local area network transceiver (20) may be a Bluetooth transceiver that communicates with the wireless device (320) and receives wireless device information (80). The wireless device information (80) may represent caller identification information, call processing information relating to the status of a call, phone status information or any suitable information. The speech processor (30) produces audio information (90) corresponding to the voice tag information (60). According to one embodiment, the speech processor (30) produces speech synthesized wireless device information (80), in-band ring tone information or any suitable information.

Abstract: A system and method for providing automatic and coordinated sharing of conversational resources, e.g., functions and arguments, between network-connected servers and devices and their corresponding applications. In one aspect, a system for providing automatic and coordinated sharing of conversational resources includes a network having a first and second network device, the first and second network device each comprising a set of conversational resources, a dialog manager for managing a conversation and executing calls requesting a conversational service, and a communication stack for communicating messages over the network using conversational protocols, wherein the conversational protocols establish coordinated network communication between the dialog managers of the first and second network device to automatically share the set of conversational resources of the first and second network device, when necessary, to perform their respective requested conversational service.

Abstract: A filter controller processes a decoded speech (DS) signal. The DS signal has a spectral envelope including a first plurality of formant peaks having different respective amplitudes. The controller produces, from the DS signal, a spectrally-flattened DS signal that is a time-domain signal. The spectrally-flattened time-domain DS signal has a spectral envelope including a second plurality of formant peaks. Each of the second plurality of formant peaks approximately coincides in frequency with a respective one of the first plurality of formant peaks. Also, the second plurality of formant peaks have approximately equal respective amplitudes. Next, the controller derives, from the spectrally-flattened time-domain DS signal, a set of filter coefficients representative of a filter response that is to be used to filter the DS signal.

Abstract: A database construction apparatus and method which construct a tree structure database are provided. First of all, consecutive node numbers are assigned to nodes for each layer, from an upper layer to a lower layer in a tree structure, in the order of the node numbers of parent nodes. Thereafter, the respective nodes are assigned child node relative numbers representing relative values between the node numbers and the node numbers of corresponding child nodes.

Abstract: A method of information retrieval using a hybrid interface is provided. The method includes providing a graphical user interface having a plurality of views with a list of potential targets within each of the views, determining a selected view from a user selection of one of the views, translating a voice input into a query, and updating the selected view based on the query to assist in information retrieval.

Abstract: The present invention is used to adapt acoustic models, quantized in subspaces, using adaptation training data (such as speaker-dependent training data). The acoustic model is compressed into multi-dimensional subspaces. A codebook is generated for each subspace. An adaptation transform is estimated, and it is applied to codewords in the codebooks, rather than to the means themselves.

Abstract: The present invention relates to systems and methods that determine intent for received data (e.g., email, voice, graphics . . . ) and respond to the data based on the intent. The systems and methods employ various combinations of features based on shallow and deep linguistic analysis (e.g., semantic and syntactic) to yield very high accuracy. The systems and methods analyze and categorize received data to locate data that can include intent. This data can be further refined by extracting features related to the intent. The features can be utilized by a classifier to determine the intent. If the intent warrants a response, the data are further scrutinized and reformulated to generate a description that is indicative of the intent. The reformulation can include representing the features in a logical form, transforming the form and generating a description of the intent that can be presented to a user visually and/or audibly.

Abstract: A Natural Language Understanding system is provided for indexing of free text documents. The system according to the invention utilizes typographical and functional segmentation of text to identify those portions of free text that carry meaning. The system then uses words and multi-word terms and phrases identified in the free to text to identify concepts in the free text. The system uses a lexicon of terms linked to a formal ontology that is independent of a specific language to extract concepts from the free text based on the words and multi-word terms in the free text. The formal ontology contains both language independent domain knowledge concepts and language dependent linguistic concepts that govern the relationships between concepts and contain the rules about how language works. The system according to the current invention may preferably be used to index medical documents and assign codes from independent coding systems, such as, SNOMED, ICD-9 and ICD-10.

Abstract: A system and method of automatically classifying a communication involving at least one human, e.g., a human-to-human telephone conversation, into predefined categories of interest, e.g., “angry customer, etc. The system automatically, or semi-automatically with user interaction, expanding user input into semantically equivalent events. The system recognizes these events, each of which is given a confidence level, and classifies the telephone conversation based on an overall confidence level. In some embodiments, a different base unit is utilized. Instead of recognizing individual words, the system recognizes composite words, each of which is pre-programmed as an atomic unit, in a given context. The recognition includes semantically relevant composite words and contexts automatically generated by the system.

Abstract: A method and system of customizing voice translation of a text to speech includes digitally recording speech samples of a known speaker, correlating each of the speech samples with a standardized audio representation, and organizing the recorded speech samples and correlated audio representations into a collection. The collection of speech samples correlated with audio representations is saved as a single voice file and stored in a device capable of translating the text to speech. The voice file is applied to a translation of text to speech so that the translated speech is customized according to the applied voice file.

Abstract: A method for adaptive long-term filtering of an audio signal, such as a decoded speech signal. The method includes measuring a smoothed periodicity of an audio signal segment, such as an audio frame, wherein the smoothed periodicity is measured by low-pass filtering an instantaneous periodicity of the audio signal segment. The periodicity of the audio signal segment is then increased in a manner that depends upon whether the smoothed periodicity is less than a predetermined threshold. By utilizing a smoothed periodicity measurement in this fashion, more accurate control of the post-filter is provided as compared to conventional solutions. Additionally, the method includes deriving filters by interpolating between filter responses of adjacent audio signal segments to minimize distortion at segment boundaries.

Abstract: An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

Abstract: A method of providing voice dialing assistance includes providing a first input to a speech recognition engine, with the first input corresponding to a speech sample provided by a caller attempting to reach an intended call recipient. A speech recognition output is generated in response to the first input. A potential call recipient is identified based upon the speech recognition output. A confirmation that the potential call recipient is the intended call recipient is implemented using a personal recording made by the potential call recipient.

Abstract: Systems and methods are provided for automatically building a native phonetic lexicon for a speech-based application trained to process a native (base) language, wherein the native phonetic lexicon includes native phonetic transcriptions (base forms) for non-native (foreign) words which are automatically derived from non-native phonetic transcriptions of the non-native words.

Abstract: Automatically normalizing a perceived loudness for a digitally encoded audio track formed of a number of channels during playback on a multimedia asset player is described. A number of auditory selectivity frequency bands are selected and for each channel in the track, a power value for each of the number of selectivity frequency bands is computed. Each of the power values is weighted by a sensitivity weighting factor and a sum value of all the weighted power values is then calculated. For the track, a perceived acoustic power value is calculated based upon the sum value for each of the channels and a normalization gain factor based upon the perceived acoustic power is calculated and associated with the track. During playback, the normalization gain factor is applied to the track.

Abstract: The present invention is a system and method for performing semantic analysis that interprets a linguistic structure output by a natural language linguistic analysis system. The semantic analysis system converts the linguistic output by the natural language linguistic analysis system into a data structure model referred to as a semantic discourse representation structure (SemDRS).