Abstract: In an embodiment, speech may be acquired from a user. A concept, that may be associated with the user, may be identified from the acquired speech. The concept may be identified by fuzzy matching one or more words in the acquired speech with data contained in a data store. The data store may be associated with the user. An action may be performed based on the identified concept.

Abstract: An apparatus and method for detecting a named-entity. The apparatus includes a candidate-named-entity extraction module that detects a candidate-named-entity based on an initial learning example and feature information regarding morphemes constituting an inputted sentence, the candidate-named-entity extraction module providing a tagged sentence including the detected candidate-named-entity; a storage module that stores information regarding a named-entity dictionary and a rule; and a learning-example-regeneration module for finally determining whether the candidate-named-entity included in the provided sentence is a valid named-entity, based on the named-entity dictionary and the rule, the learning-example-regeneration module providing the sentence as a learning example, based on a determination result, so that a probability of candidate-named-entity detection is gradually updated.

Abstract: In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

Abstract: In some embodiments, the recognition results produced by a speech processing system (which may include a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for the domain. In some embodiments, one or more of the recognition results may be evaluated to determine whether the result(s) include one or more words or phrases that, when included in a result, would change a meaning of the result in a manner that would be significant for the domain.

Abstract: In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated using one or more sets of words and/or phrases, such as pairs of words/phrases that may include words/phrases that are acoustically similar to one another and/or that, when included in a result, would change a meaning of the result in a manner that would be significant for a domain. The recognition results may be evaluated using the set(s) of words/phrases to determine, when the top result includes a word/phrase from a set of words/phrases, whether any of the alternative recognition results includes any of the other, corresponding words/phrases from the set.

Abstract: The technology of the present application provides a speech recognition system with at least two different speech recognition engines or a single engine speech recognition engine with at least two different modes of operation. The first speech recognition being used to match audio to text, which text may be words or phrases. The matched audio and text is used by a training module to train a user profile for a natural language speech recognition engine, which is at least one of the two different speech recognition engines or modes. An evaluation module evaluates when the user profile is sufficiently trained to convert the speech recognition engine from the first speech recognition engine or mode to the natural language speech recognition or mode.

Abstract: A composite language model may include a composite word predictor. The composite word predictor may include a first language model and a second language model that are combined according to a directed Markov random field. The composite word predictor can predict a next word based upon a first set of contexts and a second set of contexts. The first language model may include a first word predictor that is dependent upon the first set of contexts. The second language model may include a second word predictor that is dependent upon the second set of contexts. Composite model parameters can be determined by multiple iterations of a convergent N-best list approximate Expectation-Maximization algorithm and a follow-up Expectation-Maximization algorithm applied in sequence, wherein the convergent N-best list approximate Expectation-Maximization algorithm and the follow-up Expectation-Maximization algorithm extracts the first set of contexts and the second set of contexts from a training corpus.

Abstract: Techniques are disclosed for automatically generating structured documents based on speech, including identification of relevant concepts and their interpretation. In one embodiment, a structured document generator uses an integrated process to generate a structured textual document (such as a structured textual medical report) based on a spoken audio stream. The spoken audio stream may be recognized using a language model which includes a plurality of sub-models arranged in a hierarchical structure. Each of the sub-models may correspond to a concept that is expected to appear in the spoken audio stream. Different portions of the spoken audio stream may be recognized using different sub-models. The resulting structured textual document may have a hierarchical structure that corresponds to the hierarchical structure of the language sub-models that were used to generate the structured textual document.

Abstract: Disclosed are a distributed environment rescoring method and apparatus. A distributed environment rescoring method in accordance with the present invention includes generating a word lattice by performing voice recognition on received voice, converting the word lattice into a word confusion network formed from the temporal connection of confusion sets clustered based on temporal redundancy and phoneme similarities, generating a list of subword confusion networks based on the entropy values of the respective confusion sets included in the word confusion network, and generating a modified word confusion network by modifying a list of the subword confusion networks through distributed environment rescoring.

Abstract: A multipass processing system includes a first grammar-based speech recognition system that compares a spoken utterance to a sub-grammar. The sub-grammar includes keywords or key phrases from active grammars that each uniquely identifies one of many application engines. The first grammar-based speech recognition system generates a first grammar-based speech recognition result and a first grammar-based confidence score. A demultiplexer receives the spoken utterance through an input. The demultiplexer transmits the spoken utterance to one of many other grammar-based speech recognition systems based on the first grammar-based speech recognition-result.

Abstract: A post-processing speech system includes a natural language-based speech recognition system that compares a spoken utterance to a natural language vocabulary that includes words used to generate a natural language speech recognition result. A master conversation module engine compares the natural language speech recognition result to domain specific words and phrases. A voting engine selects a word or a phrase from the domain specific words and phrases that is transmitted to an application control system. The application control system transmits one or more control signals that are used to control an internal or an external device or an internal or an external process.

Abstract: A procurement system may include a first interface configured to receive a query from a user, a command module configured to parameterize the query, an intelligent search and match engine configured to compare the parameterized query with stored queries in a historical knowledge base and, in the event the parameterized query does not match a stored query within the historical knowledge base, search for a match in a plurality of knowledge models, and a response solution engine configured to receive a system response ID from the intelligent search and match engine, the response solution engine being configured to initiate a system action by interacting with sub-system and related databases to generate a system response.

Abstract: A computer readable storage medium embodies instructions that, when executed by a processor, cause the processor to perform a method including receiving a natural language request corresponding to an audio input associated with a user. The computer-readable storage medium further embodies instructions that, when executed, cause the processor to retrieve account information associated with the user from a domain-specific data source through a network based on the natural language request using an application configurable retrieve account data from selected ones of a plurality of domain-specific data sources, process the account information based on the natural language request to produce output information, and provide the output information to an output interface.

Abstract: Input signal recognition, such as speech recognition, can be improved by incorporating location-based information. Such information can be incorporated by creating one or more language models that each include data specific to a pre-defined geographic location, such as local street names, business names, landmarks, etc. Using the location associated with the input signal, one or more local language models can be selected. Each of the local language models can be assigned a weight representative of the location's proximity to a pre-defined centroid associated with the local language model. The one or more local language models can then be merged with a global language model to generate a hybrid language model for use in the recognition process.

Abstract: Techniques are described herein that are capable of satisfying specified intent(s) based on multimodal request(s). A multimodal request is a request that includes at least one request of a first type and at least one request of a second type that is different from the first type. Example types of request include but are not limited to a speech request, a text command, a tactile command, and a visual command. A determination is made that one or more entities in visual content are selected in accordance with an explicit scoping command from a user. In response, speech understanding functionality is automatically activated, and audio signals are automatically monitored for speech requests from the user to be processed using the speech understanding functionality.

Abstract: A white board function, and an associated method, for a wireless, or other, device. Entry of graphical and audio media pursuant to the white board function is detected and correlated. A search is performed to locate substitute graphical media amenable for substitution for the entered graphical media. If located, the substitute graphical media is substituted for the entered graphical media.

Abstract: The present invention relates to a method and apparatus for adapting a language model in response to error correction. One embodiment of a method for processing an input signal including human language includes receiving the input signal and applying a statistical language model combined with a separate, corrective language model to the input signal in order to produce a processing result.

Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.

Abstract: A name identification rule generating method, includes: generating an abstract syntax tree by removing a portion of an input sentence unrelated to a process in analysis of syntax of the input sentence by a computer; setting, in generating the abstract syntax tree, nodes corresponding to a plurality of arguments at the same layer; and generating, in generating the abstract syntax tree, a first character string pattern including a second character string corresponding to a node of the abstract syntax tree where a number of types of terminal symbols on the node is equal to or smaller than a certain multiple of a number of types of processes that call the input sentence.

Abstract: A method and communication device for determining contextual information is provided. Textual information is received from at least one of an input device and a communication interface at the communication device. The textual information is processed to automatically extract contextual data embedded in the textual information in response to the receiving. Supplementary contextual data is automatically retrieved based on the contextual data from a remote data source via the communication interface in response to the processing. The supplementary contextual data is automatically rendered at the display device in association with the contextual data in response to receiving the supplementary contextual data.

Abstract: An intelligent query system for processing voiced-based queries is disclosed, which uses semantic based processing to identify the question posed by the user by understanding the meaning of the users utterance. Based on identifying the meaning of the utterance, the system selects a single answer that best matches the user's query. The answer that is paired to this single question is then retrieved and presented to the user. The system, as implemented, accepts environmental variables selected by the user and is scalable to provide answers to a variety and quantity of user-initiated queries.

Abstract: A system and method for object detection is provided, which system and method combines parsing and classification technologies for extracting objects, e.g., events, entities or the like, from text. In exemplary embodiment, the output of a parsing technique is transformed into a model suitable as input for classification in order to provide event or entity detection results.

Abstract: A natural language request for modifying a set of subscriptions for one or more topics in a publish/subscribe topic hierarchy is received at a processing device. The natural language request includes a predetermined natural language element. The natural language request is transformed into a publish/subscribe topic string and the predetermined natural language element is transformed into a publish/subscribe symbol. The symbol represents one or more topics in the topic hierarchy. One or more subscriptions to one or more topics is modified based on the transformed topic string.

Abstract: A method and system for developing reliability models from unstructured text documents, such as text verbatim descriptions from service technicians. An ontology, or data model, and heuristic rules are used to identify and extract failure modes and parts from the text verbatim comments associated with specific labor codes from service events. Like-meaning but differently-worded terms are then merged using text similarity scoring techniques. The resultant failure modes are used to create enhanced reliability models, where component reliability is predicted in terms of individual failure modes instead of aggregated for the component. The enhanced reliability models provide improved reliability prediction for the component, and also provides insight into aspects of the component design which can be improved in the future.

Abstract: The system and method described herein may use various natural language models to deliver targeted advertisements and track advertisement interactions in voice recognition contexts. In particular, in response to an input device receiving an utterance, a conversational language processor may select and deliver one or more advertisements targeted to a user that spoke the utterance based on cognitive models associated with the user, various users having similar characteristics to the user, an environment in which the user spoke the utterance, or other criteria. Further, subsequent interaction with the targeted advertisements may be tracked to build and refine the cognitive models and thereby enhance the information used to deliver targeted advertisements in response to subsequent utterances.

Abstract: A method of searching a plurality of data files, wherein each data file includes a plurality of features. The method: determines a plurality of feature groups, wherein each feature group includes n features and n is an integer of 2 or more; expresses each data file as a file vector, wherein each component of the vector indicates the frequency of a feature group within the data file, wherein the n features which constitute a feature group do not have to be located adjacent to one another; expresses a search query using the feature groups as a vector; and searches the plurality of data files by comparing the search query expressed as a vector with the file vectors.

Abstract: A conversational, natural language voice user interface may provide an integrated voice navigation services environment. The voice user interface may enable a user to make natural language requests relating to various navigation services, and further, may interact with the user in a cooperative, conversational dialogue to resolve the requests. Through dynamic awareness of context, available sources of information, domain knowledge, user behavior and preferences, and external systems and devices, among other things, the voice user interface may provide an integrated environment in which the user can speak conversationally, using natural language, to issue queries, commands, or other requests relating to the navigation services provided in the environment.

Abstract: A system and method of refining context-free grammars (CFGs). The method includes deriving back-off grammar (BOG) rules from an initially developed CFG and utilizing the initial CFG and the derived BOG rules to recognize user utterances. Based on a response of the initial CFG and the derived BOG rules to the user utterances, at least a portion of the derived BOG rules are utilized to modify the initial CFG and thereby produce a refined CFG. The above method can carried out iterativey, with each new iteration utilizing a refined CFG from preceding iterations.

Abstract: A method and system for reporting data from a spoken dialog service is disclosed. The method comprises extracting data regarding user dialogs using a dialog logging module in the spoken dialog service, analyzing the data to identify trends and reporting the trends. The data may be presented in a visual form for easier consumption. The method may also relate to identifying data within the control or outside the control of a service provider that is used to adjust the spoken dialog service to maximize customer retention.

Abstract: An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.

Abstract: A very common problem is when people speak a language other than the language which they are accustomed, syllables can be spoken for longer or shorter than the listener would regard as appropriate. An example of this can be observed when people who have a heavy Japanese accent speak English. Since Japanese words end with vowels, there is a tendency for native Japanese to add a vowel sound to the end of English words that should end with a consonant. Illustratively, native Japanese speakers often pronounce “orange” as “orenji.” An aspect provides an automatic speech-correcting process that would not necessarily need to know that fruit is being discussed; the system would only need to know that the speaker is accustomed to Japanese, that the listener is accustomed to English, that “orenji” is not a word in English, and that “orenji” is a typical Japanese mispronunciation of the English word “orange.

Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.

Abstract: A system and method for non-speech input or keypad-aided word and spelling recognition is disclosed. The method includes generating an unweighted grammar, selecting a database of words, generating a weighted grammar using the unweighted grammar and a statistical letter model trained on the database of words, receiving speech from a user after receiving the non-speech input and after generating the weighted grammar, and performing automatic speech recognition on the speech and non-speech input using the weighted grammar If a confidence is below a predetermined level, then the method includes receiving non-speech input from the user, disambiguating possible spellings by generating a letter lattice based on a user input modality, and constraining the letter lattice and generating a new letter string of possible word spellings until a letter string is correctly recognized.

Abstract: A method and apparatus derive a dynamic grammar composed of a subset of a plurality of data elements that are each associated with one of a plurality of reference identifiers. The present invention generates a set of selection identifiers on the basis of a user-provided first input identifier and determines which of these selection identifiers are present in a set of pre-stored reference identifiers. The present invention creates a dynamic grammar that includes those data elements that are associated with those reference identifiers that are matched to any of the selection identifiers. Based on a user-provided second identifier and on the data elements of the dynamic grammar, the present invention selects one of the reference identifiers in the dynamic grammar.

Abstract: A machine based analysis engine method to obtain a better understanding of written texts by using Contextual and Semantic Analysis with Artificial Intelligence is described. This method applies to rendering refined targeted advertisement's display. This method applies to rendering enhanced search engines' results. This method allows natural language awareness rendering accurate results. This method applies to any texts enhancing document translation.

Abstract: An integrated language model includes an upper-level language model component and a lower-level language model component, with the upper-level language model component including a non-terminal and the lower-level language model component being applied to the non-terminal. The upper-level and lower-level language model components can be of the same or different language model formats, including finite state grammar (FSG) and statistical language model (SLM) formats. Systems and methods for making integrated language models allow designation of language model formats for the upper-level and lower-level components and identification of non-terminals. Automatic non-terminal replacement and retention criteria can be used to facilitate the generation of one or both language model components, which can include the modification of existing language models.

Abstract: The invention provides a system and method for improving speech recognition. A computer software system is provided for implementing the system and method. A user of the computer software system may speak to the system directly and the system may respond, in spoken language, with an appropriate response. Grammar rules may be generated automatically from sample utterances when implementing the system for a particular application. Dynamic grammar rules may also be generated during interaction between the user and the system. In addition to arranging searching order of grammar files based on a predetermined hierarchy, a dynamically generated searching order based on history of contexts of a single conversation may be provided for further improved speech recognition.

Abstract: A speech recognition engine is provided with an acoustic model and a layered grammar and dictionary library. The layered grammar and dictionary library includes a language and non-grammar layer that supplies types of rules a grammar definition layer can use and defines non-grammar the speech recognition engine should ignore. The layered grammar and dictionary library also includes a dictionary layer that defines phonetic transcriptions for word groups the speech recognition engine is meant to recognize when voice input is received. The layered grammar and dictionary library further includes a grammar definition layer that applies rules from the language and non-grammar layer to define combinations of word groups the speech recognition system is meant to recognize. Voice input is received at a speech recognition engine and is processed using the acoustic model and the layered grammar and dictionary library.

Abstract: A system and method for providing a natural language interface to a database or the Internet. The method provides a response from a database to a natural language query. The method comprises receiving a user query, extracting key data from the user query, submitting the extracted key data to a data base search engine to retrieve a top n pages from the data base, processing of the top n pages through a natural language dialog engine and providing a response based on processing the top n pages.

Abstract: A dialogue system uses an extended domain in order to have a dialogue with a user using natural language. If a dialogue pattern actually input by the user is different from a dialogue pattern predicted by an expert, an extended domain generated in real time based on user input is used and an extended domain generated in advance is used to have a dialogue with the user.

Abstract: The present invention relates to a communication system, comprising a database including classes of speech templates, in particular, classified according to a predetermined grammar; an input configured to receive and to digitize speech signals corresponding to a spoken utterance; a speech recognizer configured to receive and recognize the digitized speech signals; and wherein the speech recognizer is configured to recognize the digitized speech signals based on speech templates stored in the database and a predetermined grammatical structure.

Abstract: A system, apparatus, method, and computer program product encoding the method are provided for expectation fulfillment evaluation. The system includes a natural language processing component that extracts sets of normalized tasks from an input expectation document and an input fulfillment document. A task list comparison component compares the two sets of tasks and identifies each match between a normalized task in the first set and a normalized task in the second set, each normalized task in the first set which has no matching task in the second set, and each normalized task in the second set which has no matching task in the first set. A report generator outputs a report based on the comparison.

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

Abstract: A speech recognition module includes an acoustic front-end module, a sound detection module, and a word detection module. The acoustic front-end module generates a plurality of representations of frames from a digital audio signal and generates speech characteristic probabilities for the plurality of frames. The sound detection module determines a plurality of estimated utterances from the plurality of representations and the speech characteristic probabilities. The word detection module determines one or more words based on the plurality of estimated utterances and the speech characteristics probabilities.

Abstract: The invention can recognize all languages and input words. It needs m unknown voices to represent m categories of known words with similar pronunciations. Words can be pronounced in any languages, dialects or accents. Each will be classified into one of m categories represented by its most similar unknown voice. When user pronounces a word, the invention finds its F most similar unknown voices. All words in F categories represented by F unknown voices will be arranged according to their pronunciation similarity and alphabetic letters. The pronounced word should be among the top words. Since we only find the F most similar unknown voices from m (=500) unknown voices and since the same word can be classified into several categories, our recognition method is stable for all users and can fast and accurately recognize all languages (English, Chinese and etc.) and input much more words without using samples.

Abstract: A method of operating a voice-enabled business directory search system includes receiving category-business pairs, each category-business pair including a business category and a specific business, and establishing a data structure having nodes based on the category-business pairs. Each node of the data structure is associated with one or more business categories and a speech recognition language model for recognizing specific businesses associated with the one or more businesses categories.

Abstract: A system and method generate artistic multimedia representations of user-input texts, spoken or loaded narratives, theatrical scripts, or other linguistic corpus types, via a user interface, or batch interface, by classifying component words, and/or phrases into lexemes and/or parts of speech, and interpreting said classifications to construct playable structures. A database of natural language grammatical rules, a set of media objects, parameters, and rendering directives, and an algorithm facilitate the generation of sequential scenes from grammatical representations, convert user-input texts into playable structures of graphics, sounds, animations, and modifications, where playable structures may be combined to create a scene, or multiple scenes, and may be played in the order of occurrence in the input text as a sequential and timed multimedia representation of the input, and subsequently output, in real-time, or stored in memory for later output, via output devices such as a monitor and/or speakers.

Abstract: Methods are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation, of the model for the word or various models for the various words, based on the error rate. Apparatus are disclosed for identifying possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system.

Abstract: Techniques to provide automatic speech recognition at a local device are described. An apparatus may include an audio input to receive audio data indicating a task. The apparatus may further include a local recognizer component to receive the audio data, to pass the audio data to a remote recognizer while receiving the audio data, and to recognize speech from the audio data. The apparatus may further include a federation component operative to receive one or more recognition results from the local recognizer and/or the remote recognizer, and to federate a plurality of recognition results to produce a most likely result. The apparatus may further include an application to perform the task indicated by the most likely result. Other embodiments are described and claimed.

Abstract: Smart Mark-up or highlighting delimits a rule using ontology technology to identify words and fields as objects and/or possible values in the rule. These technologies support the user in formalizing parts of the rules in a manner consistent with the system's data.