Abstract: In embodiments of the present invention improved capabilities are described for a user interacting with a mobile communication facility, where speech presented by the user is recorded using a mobile communication facility resident capture facility. The recorded speech may be recognized using an external speech recognition facility to produce an external output and a resident speech recognition facility to produce an internal output, where at least one of the external output and the internal output may be selected based on a criteria.

Abstract: A method for parsing a verbal expression received from a user to determine whether or not the expression contains a multiple-goal command is described. Specifically, known techniques are applied to extract terms from the verbal expression. The extracted terms are assigned to categories. If two or more terms are found in the parsed verbal expression that are in associated categories and that do not overlap one another temporally, then the confidence levels of these terms are compared. If the confidence levels are similar, then the terms may be parallel entries in the verbal expression and may represent multiple goals. If a multiple-goal command is found, then the command is either presented to the user for review and possible editing or is executed. If the parsed multiple-goal command is presented to the user for review, then the presentation can be made via any appropriate interface including voice and text interfaces.

Abstract: A mobile system is provided that includes speech-based and non-speech-based interfaces for telematics applications. The mobile system identifies and uses context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for users that submit requests and/or commands in multiple domains. The invention creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command. The invention may organize domain specific behavior and information into agents, that are distributable or updateable over a wide area network.

Abstract: A method (and system) of determining confusable list items and resolving this confusion in a spoken dialog system includes receiving user input, processing the user input and determining if a list of items needs to be played back to the user, retrieving the list to be played back to the user, identifying acoustic confusions between items on the list, changing the items on the list as necessary to remove the acoustic confusions, and playing unambiguous list items back to the user.

Abstract: Methods, apparatus, and products are disclosed for supporting multi-lingual user interaction with a multimodal application, the application including a plurality of VoiceXML dialogs, each dialog characterized by a particular language, supporting multi-lingual user interaction implemented with a plurality of speech engines, each speech engine having a grammar and characterized by a language corresponding to one of the dialogs, with the application operating on a multimodal device supporting multiple modes of interaction including a voice mode and one or more non-voice modes, the application operatively coupled to the speech engines through a VoiceXML interpreter, the VoiceXML interpreter: receiving a voice utterance from a user; determining in parallel, using the speech engines, recognition results for each dialog in dependence upon the voice utterance and the grammar for each speech engine; administering the recognition results for the dialogs; and selecting a language for user interaction in dependence upon

Abstract: Improved methods of presenting speech prompts to a user as part of an automated system that employs speech recognition or other voice input are described. The invention improves the user interface by providing in combination with at least one user prompt seeking a voice response, an enhanced user keyword prompt intended to facilitate the user selecting a keyword to speak in response to the user prompt. The enhanced keyword prompts may be the same words as those a user can speak as a reply to the user prompt but presented using a different audio presentation method, e.g., speech rate, audio level, or speaker voice, than used for the user prompt. In some cases, the user keyword prompts are different words from the expected user response keywords, or portions of words, e.g., truncated versions of keywords.

Abstract: A method and an apparatus for performing and controlling speech recognition and enrolment are provided. The method for performing speech recognition and enrolment includes: receiving a Speech Enrolment Start Request and a Speech Recognition Request sent from a media gateway controller (MGC); performing speech recognition and enrolment according to the Speech Enrolment Start Request and the Speech Recognition Request, and obtaining a recognition and enrolment result; and feeding back the recognition and enrolment result to the MGC.

Abstract: An arrangement is described for conducting natural language dialogs with a user on a mobile device using automatic speech recognition (ASR) and multiple different dialog applications. A user interface provides for user interaction with the dialogue applications in natural language dialogs. An ASR engine processes unknown speech inputs from the user to produce corresponding speech recognition results. A dialog concept module develops dialog concept items from the speech recognition results and stores the dialog concept items and additional dialog information in a dialog concept database. A dialog processor accesses dialog concept database information and coordinates operation of the ASR engine and the dialog applications to conduct with the user a plurality of separate parallel natural language dialogs in the dialog applications.

Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.

Abstract: An automatic language-processing system uses a human-curated lexicon to associate words and word groups with broad sentiments such as fear or anger, and topics such as accounting fraud or earnings projections. Grammar processing further characterizes the sentiments or topics with logical (“is” or “is not”), conditional (probability), temporal (past, present, future), quantitative (larger/smaller, higher/lower, etc.), and speaker identification (“I” or “He” or “Alan Greenspan”) measures. Information about the characterized sentiments and topics found in electronic messages is stored in a database for further analysis, display, and use in automatic trading systems.

Abstract: A speech recognition device includes, a speech recognition section that conducts a search, by speech recognition, on audio data stored in a first memory section to extract word-spoken portions where plural words transferred are each spoken and, of the word-spoken portions extracted, rejects the word-spoken portion for the word designated as a rejecting object; an acquisition section that obtains a derived word of a designated search target word, the derived word being generated in accordance with a derived word generation rule stored in a second memory section or read out from the second memory section; a transfer section that transfers the derived word and the search target word to the speech recognition section, the derived word being set to the outputting object or the rejecting object by the acquisition section; and an output section that outputs the word-spoken portion extracted and not rejected in the search.

Abstract: Systems and methods are provided for adding punctuations. For example, one or more first feature units are identified in a voice file taken as a whole; the voice file is divided into multiple segments: one or more second feature units are identified in the voice file; a first aggregate weight of first punctuation states of the voice file and a second aggregate weight of second punctuation states of the voice file are determined, using a language model established based on word separation and third semantic features; a weighted calculation is performed to generate a third aggregate weight based on at least information associated with the first aggregate weight and the second aggregate weight; and one or more final punctuations are added to the voice file based on at least information associated with the third aggregate weight.

Abstract: An artificially intelligent or rule-based system to assist teams or groups become more effective by improving the communication process between members of the team or group. The system helps members share information, negotiate more effectively and make better group decisions. The system is designed to allow users to provide feedback to the system regarding undetected emotional feelings of any one user to all users of the system.

Abstract: The method comprises steps of: a) for each point of interest of each image, calculating a local gradient descriptor and a local movement descriptor; b) forming microstructures of n points of interest, each defined by a tuple of order n, with n?1; c) determining, for each tuple of a vector of structured visual characteristics (d0 . . . d3 . . . ) based on the local descriptors; d) for each tuple, mapping this vector by a classification algorithm selecting a single codeword among a set of codewords forming a codebook (CB); e) generating an ordered time series of the codewords (a0 . . . a3 . . . ) for the successive images of the video sequence; and f) measuring, by means of a function of the String Kernel type, the similarity of the time series of codewords with another time series of codewords coming from another speaker.

Abstract: The method comprises steps of: a) forming a starting set of microstructures of n points of interest, each defined by a tuple of order n, with n?1; b) determining, for each tuple, associated structured visual characteristics, based on local gradient and/or movement descriptors of the points of interest; and c) iteratively searching for and selecting the most discriminant tuples. Step c) operates by: c1) applying to the set of tuples an algorithm of the Multi-Kernel Learning MKL type; c2) extracting a sub-set of tuples producing the highest relevancy scores; c3) aggregating to these tuples an additional tuple to obtain a new set of tuples of higher order; c4) determining structured visual characteristics associated to each aggregated tuple; c5) selecting a new sub-set of most discriminant tuples; and c6) reiterating steps c1) to c5) up to a maximal order N.

Abstract: This specification describes technologies relating to visual representations indicating segments of audio data. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving digital audio data including hierarchical segment information, the hierarchical segment information identifying one or more segments of the audio data for each of multiple of segment types and displaying a visual representation of the audio data at a first zoom level in an interface, the visual representation displaying audio data as a function of time on a time axis and a feature on a feature axis, the visual representation further including a display of identifiers for each segment of one or more segments of a first segment type. Other embodiments of this aspect include corresponding systems, apparatus, and computer program products.

Abstract: Example embodiments of the present invention may include a method that provides transcribing spoken utterances occurring during a call and assigning each of the spoken utterances with a corresponding set of first classifications. The method may also include determining a confidence rating associated with each of the spoken utterances and the assigned set of first classifications, and performing at least one of reclassifying the spoken utterances with new classifications based on at least one additional classification operation, and adding the assigned first classifications and the corresponding plurality of spoken utterances to a training data set.

Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.

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: A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2?n?N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n?1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

Abstract: According to example configurations, a translation quality assessment application (e.g., system) receives a set of text derived from a translation of an audio signal. The translation quality assessment application aligns and compares the received set of text to reference text to identify occurrence of speech-to-text translation errors in the set of text. For each of the errors, the translation quality assessment application identifies a type associated with the error and retrieves an appropriate weighted coefficient. For example, the translation quality assessment application produces a respective weighted value for each error based on the weighted coefficients. A magnitude of each of the weighted values varies depending on a type of the error that occurred during the translation. The translation quality assessment application utilizes the weighted values to generate a metric indicating a level of quality of the set of captioned text with respect to the set of reference text.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving audio data that corresponds to an utterance, obtaining a first transcription of the utterance that was generated using a limited speech recognizer. The limited speech recognizer includes a speech recognizer that includes a language model that is trained over a limited speech recognition vocabulary that includes one or more terms from a voice command grammar, but that includes fewer than all terms of an expanded grammar. A second transcription of the utterance is obtained that was generated using an expanded speech recognizer. The expanded speech recognizer includes a speech recognizer that includes a language model that is trained over an expanded speech recognition vocabulary that includes all of the terms of the expanded grammar. The utterance is classified based at least on a portion of the first transcription or the second transcription.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations.

Abstract: A text processing apparatus is provided with a segment determination unit 36 and a descriptive content determination unit 33. The segment determination unit 36 determines, with respect to a homogeneous segment that is similar to segments constituting a first text which is set as an analysis target (analysis target text) and that is included in another first text, whether the content thereof is included in a second text. The descriptive content determination unit 33 determines whether each segment constituting the analysis target text should be described in a corresponding second text, based on the determination result.

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 and system for entering information into a software application resident on a mobile communication facility is provided. The method and system may include recording speech presented by a user using a mobile communication facility resident capture facility, transmitting the recording through a wireless communication facility to a speech recognition facility, transmitting information relating to the software application to the speech recognition facility, generating results utilizing the speech recognition facility using an unstructured language model based at least in part on the information relating to the software application and the recording, transmitting the results to the mobile communications facility, loading the results into the software application and simultaneously displaying the results as a set of words and as a set of application results based on those words.

Abstract: A local computing device may receive an utterance from a user device. In response to receiving the utterance, the local computing device may obtain a text string transcription of the utterance, and determine a response mode for the utterance. If the response mode is a text-based mode, the local computing device may provide the text string transcription to a target device. If the response mode is a non-text-based mode, the local computing device may convert the text string transcription into one or more commands from a command set supported by the target device, and provide the one or more commands to the target device.

Abstract: Techniques for generating language models. The techniques include: obtaining language data comprising training data and associated values for one or more metadata attributes, the language data comprising a plurality of instances of language data, an instance of language data comprising an instance of training data and one or more metadata attribute values associated with the instance of training data; identifying, by processing the language data using at least one processor, a set of one or more of the metadata attributes to use for clustering the instances of training data into a plurality of clusters; clustering the training data instances based on their respective values for the identified set of metadata attributes into the plurality of clusters; and generating a language model for each of the plurality of clusters.

Abstract: Embodiments of a dialog system that employs a corpus-based approach to generate responses based on a given number of semantic constraint-value pairs are described. The system makes full use of the data from the user input to produce dialog system responses in combination with a template generator. The system primarily utilizes constraint values in order to realize efficiencies based on the more frequent tasks performed in real dialog systems although rhetorical or discourse aspects of the dialog could also be included in a similar way, that is, labeling the data with such information and performing a training process. The benefits of this system include higher quality user-aligned responses, broader coverage, faster response time, and shorter development cycles.

Abstract: Text analysis methods, text analysis apparatuses, and articles of manufacture are described according to some aspects. In one aspect, a text analysis method includes accessing information indicative of data content of a collection of text comprising a plurality of different topics, using a computing device, analyzing the information indicative of the data content, and using results of the analysis, identifying a presence of a new topic in the collection of text.

Abstract: A method, a system, and computer readable medium comprising instructions for analyzing data of a speech application are provided. The method comprises defining a set of data collection objects for a call flow in a speech application, collecting data using the set of data collection objects during execution of the speech application, and analyzing the data using a benchmarking and bootstrapping engine, storing the data in a repository, and presenting the data for analysis.

Abstract: A referring expression processor which uses a probabilistic model and in which referring expressions including descriptive, anaphoric and deictic expressions are understood and generated in the course of dialogue is provided. The referring expression processor according to the present invention includes: a referring expression processing section which performs at least one of understanding and generation of referring expressions using a probabilistic model constructed with a referring expression Bayesian network, each referring expression Bayesian network representing relationships between a reference domain (D) which is a set of possible referents, a referent (X) in the reference domain, a concept (C) concerning the referent and a word (W) which represents the concept; and a memory which stores data necessary for constructing the referring expression Bayesian network.

Abstract: A method, computer program product, and system are provided for performing a voice command on a client device. The method can include translating, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command and generating a first query result using the first machine-readable voice command to query a client database. In addition, the audio stream can be transmitted to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer. Further, the method can include receiving a second query result from the remote server device, where the second query result is generated by the remote server device using the second machine-readable voice command and displaying the first query result and the second query result on the client device.

Abstract: A recognition dictionary creation device identifies the language of a reading of an inputted text which is a target to be registered and adds a reading with phonemes in the language identified thereby to the target text to be registered, and also converts the reading of the target text to be registered from the phonemes in the language identified thereby to phonemes in a language to be recognized which is handled in voice recognition to create a recognition dictionary in which the converted reading of the target text to be registered is registered.

Abstract: The invention provides a dialogue-based learning apparatus through dialogue with users comprising: a speech input unit (10) for inputting speeches; a speech recognition unit (20) for recognizing the input speech; and a behavior and dialogue controller (30) for controlling behaviors and dialogues according to speech recognition results, wherein the behavior and dialogue controller (30) has a topic recognition expert (34) to memorise contents of utterances and to retrieve the topic that best matches the speech recognition results, and a mode switching expert (35) to control mode switching in accordance with a user utterance, wherein the mode switching expert switches modes in accordance with a user utterance, wherein the topic recognition expert registers a plurality words in the utterance as topics in first mode, performs searches from among the registered topics, and selects the maximum likelihood topic in second mode.

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: Potential linguistic errors within a sequence of words of a sentence are identified based on analysis of a configurable sliding window. The analysis is performed based on an assumption that if a sequence of words occurs frequently enough within a large, well-formed corpus, its joint probability for occurring in a sentence is very likely to be greater than the same words randomly ordered.

Abstract: Methods and systems for model-driven candidate sorting based on audio cues for evaluating digital interviews are described. In one embodiment, a processing device converts audio data of a candidate in a digital interview into voice-to-text data. An audio cue generator executing on the processing device, generates audio cues of the digital interview based on the voice-to-text data. The audio cues are applied to a prediction model to predict an achievement index for the candidate based on the audio cues. The processing device displays the candidate in a list of candidates based on the achievement index. The list of candidates is sorted according to the candidates' achievement index.

Abstract: Methods and systems are provided for assisted speech input. In one example, the method may involve (a) designating a first node of a tree as a current node. Each node in the tree is associated with a speech input data, and the first node includes one or more child nodes. The method may further involve (b) removing all nodes from a first group of nodes, (c) copying each child node of the current node to the first group, (d) removing all nodes from a second group of nodes, (e) moving a selection of nodes from the first group to the second group, and (f) presenting information associated with each node in the second group. The method may include additional elements depending on whether there is a match between a received speech input and a child node of the current node.

Abstract: A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Abstract: An automated arrangement is described for conducting natural language interactions with a human user. A user interface is provided for user communication in a given active natural language interaction with a natural language application during an automated dialog session. An automatic speech recognition (ASR) engine processes unknown user speech inputs from the user interface to produce corresponding speech recognition results. A natural language concept module processes the speech recognition results to develop corresponding natural language concept items. A concept item storage holds selected concept items for reuse in a subsequent natural language interaction with the user during the automated dialog session.

Abstract: A system and method for automatically generating sentences in a language is disclosed. The system comprising a grammar processor for converting an input grammar into a hierarchical representation, and a grammar explorer module for traversing the grammar hierarchy based on an explore specification, which defines what nodes of the hierarchy should be explored. The explorer module takes the exploration specification as input and traverses the hierarchy according to the exploration types specified in the exploration specification. The system and method can be used to automatically generate assembly instructions for a microprocessor given its assembly language grammar, to generate sentences of a natural language like English from its grammar and to generate programs in a high-level programming language like C.

Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.

Abstract: Systems and methods are disclosed herein to a method for presenting topics of conversation during a call comprising: connecting, by a computer, a first device and a second device over a network; opening, by a computer, an audio channel that facilitates audio communication between a first user of the first device and a second user of the second device; receiving, by a computer, an audio stream over the audio channel; analyzing, by a computer, the audio stream to determine spoken words said by either the first or second users; correlating, by a computer, the determined spoken words to determine a topic of conversation; and displaying, by a computer, the topic of conversation in an information post to a remote terminal connected to the network.

Abstract: Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for handling missing speech data. The computer-implemented method includes receiving speech with a missing segment, generating a plurality of hypotheses for the missing segment, identifying a best hypothesis for the missing segment, and recognizing the received speech by inserting the identified best hypothesis for the missing segment. In another method embodiment, the final step is replaced with synthesizing the received speech by inserting the identified best hypothesis for the missing segment. In one aspect, the method further includes identifying a duration for the missing segment and generating the plurality of hypotheses of the identified duration for the missing segment. The step of identifying the best hypothesis for the missing segment can be based on speech context, a pronouncing lexicon, and/or a language model. Each hypothesis can have an identical acoustic score.

Abstract: A method of building a database for a linguistic recognition device is provided The method includes storing common linguistic model data configured to infer a word or a sentence from a character acquired by recognizing a language input by a user in a storage section of a linguistic recognition device, collecting recognition-related information related to the user after storing the common linguistic data, and analyzing the collected recognition-related information to be stored as individual linguistic model data.

Abstract: A system includes one or more computer processors that are configured to receive data relating to a composition of a target group, receive logged communications of the target group, extract textual information from the logged communications, analyze the textual information using statistical and linguistic sentiment analysis techniques, identify an individual or sub-group from the target group as a function of the analysis of the textual information, and display on a user interface or transmit to another processor the identified individual or sub-group of the target group and to display on the user interface or transmit to another processor a sentiment assessment of the identified individual or sub-group as a function of the statistical and linguistic sentiment analysis.

Abstract: Training speech recognizers, e.g., their language or acoustic models, using actual user data is useful, but retaining personally identifiable information may be restricted in certain environments due to regulations. Accordingly, a method or system is provided for enabling training of a language model which includes producing segments of text in a text corpus and counts corresponding to the segments of text, the text corpus being in a depersonalized state. The method further includes enabling a system to train a language model using the segments of text in the depersonalized state and the counts. Because the data is depersonalized, actual data may be used, enabling speech recognizers to keep up-to-date with user trends in speech and usage, among other benefits.

Abstract: Training speech recognizers, e.g., their language or acoustic models, using actual user data is useful, but retaining personally identifiable information may be restricted in certain environments due to regulations. Accordingly, a method or system is provided for enabling training of an acoustic model which includes dynamically shredding a speech corpus to produce text segments and depersonalized audio features corresponding to the text segments. The method further includes enabling a system to train an acoustic model using the text segments and the depersonalized audio features. Because the data is depersonalized, actual data may be used, enabling speech recognizers to keep up-to-date with user trends in speech and usage, among other benefits.

Abstract: Data associated with spoken language may be obtained. An analysis of the obtained data may be initiated for understanding of the spoken language using a deep convex network that is integrated with a kernel trick. The resulting kernel deep convex network may also be constructed by stacking one shallow kernel network over another with concatenation of the output vector of the lower network with the input data vector. A probability associated with a slot that is associated with slot-filling may be determined, based on local, discriminative features that are extracted using the kernel deep convex network.