Abstract: A system, apparatus and a method for determining distinguishable data, includes processing input data into a plurality of elements, calculating distinguishability of the plurality of elements using phonetic vowels, and determining distinguishable elements from among the plurality of elements, according to the distinguishability calculation.

Abstract: A computer-implemented method is provided for data augmentation. The method includes receiving a set of different base models already pretrained and a set of different test cases. The method further includes collecting a plurality of prediction results of the set of different test cases from the set of different base models. The method also includes identifying a test case as a candidate for the data augmentation based on a number of models in the set of different base models which fail to solve the test case. The method additionally includes augmenting, by a processor device, the identified test case with additional data to form an augmented training dataset. The method further includes retraining at least some of the different base models with the augmented training dataset.

Abstract: Several round-efficient solitary multi-party computation protocols with guaranteed output delivery are disclosed. A plurality of input devices and an output device can collectively perform a computation using methods such as fully homomorphic encryption. The output of the computation is only known to the output device. Some number of these devices may be corrupt. However, even in the presence of corrupt devices, the output device can still either generate a correct output or identify that the computation was compromised. These protocols operate under different assumptions regarding the communication infrastructure (e.g., broadcast vs point-to-point), the number of participating devices, and the number of corrupt devices. These protocols are round-efficient in that they require a minimal number of communication rounds to calculate the result of the multi-party computation.

Abstract: Provided is a system which allows a learner who is a non-native speaker of a given language to intuitively improve pronunciation of the language. A pronunciation conversion apparatus includes a conversion section which converts a first feature value corresponding to a first speech signal obtained when a first speaker who speaks a given language as his/her native language speaks another language such that the first feature value approaches a second feature value corresponding to a second speech signal obtained when a second speaker who speaks the other language as his/her native language speaks the other language, each of the first feature value and the second feature value is a feature value capable of representing a difference in pronunciation, and a speech signal obtained from the first feature value after the conversion is presented to the first speaker.

Abstract: Statistical models for predicting minimum number of step data of an attacker and reliability functions of a computer network system are described. The models are based on utilizing vulnerability information along with an attack graph. Using the model, it is possible to identify the interaction among vulnerabilities and individual variables or risk factors that drive the minimum number of step data. Gaining a better understanding of the relationship between the vulnerabilities and their interactions can provide security administrators with a better view and understanding of their security status.

Abstract: In some examples, voice modulation based voice authentication may include receiving a signal that represents a modulated voice of a user, and analyzing the signal to ascertain a specified code for a specified time period. Voice modulation based voice authentication may further include determining, for the specified time period, an authentication code from a plurality of authentication codes, and comparing the specified code to the authentication code. In response to a determination that the specified code matches the authentication code, voice modulation based voice authentication may further include authenticating the user.

Abstract: Provided are methods and systems for performing a secure probabilistic analytic using an encrypted analytics matrix. An example method includes acquiring, by a client, an analytic, analytic parameters associated with the analytic, and a homomorphic encryption scheme including a public key for encryption and a private key for decryption. The method further includes generating, using the encryption scheme, an analytic matrix based on the analytic and analytic parameters, and sending the analytic matrix and the encryption scheme to at least one server. The method includes generating, by the server and based on the encryption scheme, set of terms from a data set, evaluating the analytic matrix over the set of terms to obtain an encrypted result, and estimating a probabilistic error of the encrypted result. The method further includes sending, by the server, the encrypted result and the probabilistic error to the client where the encrypted result is decrypted.

Abstract: An apparatus includes processor(s) to: generate a set of candidate n-grams based on probability distributions from an acoustic model for candidate graphemes of a next word most likely spoken following at least one preceding word spoken within speech audio; provide the set of candidate n-grams to multiple devices; provide, to each node device, an indication of which candidate n-grams are to be searched for within the n-gram corpus by each node device to enable searches for multiple candidate n-grams to be performed, independently and at least partially in parallel, across the node devices; receive, from each node device, an indication of a probability of occurrence of at least one candidate n-gram within the speech audio; based on the received probabilities of occurrence, identify the next word most likely spoken within the speech audio; and add the next word most likely spoken to a transcript of the speech audio.

Abstract: Systems, devices, media, and methods are presented for determining a level of abusive network behavior suspicion for groups of entities and for identifying suspicious entity groups. A suspiciousness metric is developed and used to evaluate a multi-view graph across multiple views where entities are associated with nodes of the graph and attributes of the entities are associated with levels of the graph.

Abstract: A method for providing a natural language conversation, which is implemented by an interactive agent system, may include receiving a natural language input, determining a user intent based on the natural language input, and providing a natural language response corresponding to the natural language input, based on the natural language input and/or the determined user intent, which is associated with execution of a specific task, provision of specific information, and/or a simple statement. The provision of the natural language response includes determining whether a first condition is satisfied based on whether it is possible to obtain all sufficient information from the natural language input, without having to request additional information, and when the first condition is satisfied, determining whether a second condition is satisfied and providing a natural language response belonging to a category of substantial replies when the second condition is satisfied.

Abstract: [Object] To provide a communication system and a communication control method capable of obtaining reliable feedback from a user further naturally through a conversation with an agent without imposing a burden on the user. [Solution] The communication system includes: a communication unit configured to receive request information for requesting feedback on a specific experience of a user; an accumulation unit configured to accumulate the feedback received from a client terminal of the user via the communication unit; and a control unit configured to perform control such that a question for requesting the feedback on the specific experience of the user based on the request information is transmitted to the client terminal of the user at a timing according to context of the user, and feedback input by the user in response to the question output as speech of an agent via the client terminal is received.

Abstract: The present disclosure discloses a voice conversion training method. The method includes: forming a first training data set including a plurality of training voice data groups; selecting two of the training voice data groups from the first training data set to input into a voice conversion neural network for training; forming a second training data set including the first training data set and a first source speaker voice data group; inputting one of the training voice data groups selected from the first training data set and the first source speaker voice data group into the network for training; forming the third training data set including the second source speaker voice data group and the personalized voice data group that are parallel corpus with respect to each other; and inputting the second source speaker voice data group and the personalized voice data group into the network for training.

Abstract: A device having a voice-based interface activates or “wakes” when it detects an utterance that includes a wakeword. The device includes a digital-signal processor (DSP) that implements a first, lower-power speech-processing component that detects when captured audio includes the wakeword; the first speech-processing component then activates a second, higher-accuracy wakeword detection component that confirms that the captured audio includes the wakeword. The device may configure a wakeword-detection parameter, speaker-identification parameter, and/or wakeword-detection model of the first speech-processing component based on device-use data corresponding to the device, such as an environment of the device and/or a usage pattern of the user of the device.

Abstract: An apparatus includes processor(s) to: generate a set of candidate n-grams based on probability distributions from an acoustic model for candidate graphemes of a next word most likely spoken following at least one preceding word spoken within speech audio; provide the set of candidate n-grams to multiple devices; provide, to each node device, an indication of which candidate n-grams are to be searched for within the n-gram corpus by each node device to enable searches for multiple candidate n-grams to be performed, independently and at least partially in parallel, across the node devices; receive, from each node device, an indication of a probability of occurrence of at least one candidate n-gram within the speech audio; based on the received probabilities of occurrence, identify the next word most likely spoken within the speech audio; and add the next word most likely spoken to a transcript of the speech audio.

Abstract: A system and method are presented for the automatic filtering of test utterance mismatches in automatic speech recognition (ASR) systems. Test data are evaluated for match between audio and text in a language-independent manner. Utterances having mismatch are identified and isolated for either removal or manual verification to prevent incorrect measurements of the ASR system performance. In an embodiment, contiguous stretches of low probabilities in every utterance are searched for and removed. Such segments may be intra-word or cross-word. In another embodiment, scores may be determined using log DNN probability for every word in each utterance. Words may be sorted in the order of the scores and those utterances containing the least word scores are removed.

Abstract: A processor receives inputs from a dialog between an agent and a user performed over a communication channel A knowledge base is stored, comprising entries with a subset of said entries defined as higher priority. A match is detected between an input from said dialog and a plurality of said knowledge base entries. At least one of said plurality of entries is retrieved corresponding to said match. The at least one of said plurality of entries is pushed as an output to one or more of a device operated by said user and at least one device operated by one of said user and said agent. A further match is detected between an input from said dialog and a higher priority entry in said knowledge base and pushed to said at least one device while the dialog is ongoing.

Abstract: Embodiments are associated with a speaker-independent acoustic model capable of classifying senones based on input speech frames and on first parameters of the speaker-independent acoustic model, a speaker-dependent acoustic model capable of classifying senones based on input speech frames and on second parameters of the speaker-dependent acoustic model, and a discriminator capable of receiving data from the speaker-dependent acoustic model and data from the speaker-independent acoustic model and outputting a prediction of whether received data was generated by the speaker-dependent acoustic model based on third parameters.

Abstract: A method includes receiving a voice input via a microphone of an electronic device, and determining whether the voice input contains speech from an authorized user of the electronic device or speech from an unauthorized user. The method includes in response to determining that the voice input contains speech from the authorized user: determining whether the speech contains private speech or public speech; in response to determining that the speech contains private speech, processing the voice input through a local automatic speech recognition (ASR) engine within the electronic device, the local ASR engine converting the voice input from audio format to text format and outputting a text transcription of the private speech; and in response to determining that the speech does not contain private speech, forwarding the voice input through a communication interface associated with a network-connected external device for processing the voice input at the network-connected external device.

Abstract: Aspects of software vulnerability prediction are described. In some examples vulnerability data is obtained from a vulnerability database for the software. The total cumulative vulnerability of the software is estimated using the vulnerability data. The total cumulative vulnerability is based at least in part on a time based nonlinear differential equation model. The time based nonlinear differential equation model generates a complete vulnerability life cycle. A graph is generated to display a cyclic increasing behavior of the complete vulnerability life cycle of the software.

Abstract: A converter system for multi-component systems, comprising a multi-component system adjustment module, includes: an input/output unit, an adjustment unit configured to adjust at least one primary component of a primary multi-component system for each of the at least one primary component given as a probability distribution, a certainty evaluation unit configured to evaluate a certainty parameter of the primary multi-component system, and compare the certainty parameter with a certainty threshold, and a prompt selection unit configured to, if the certainty parameter of the primary multi-component system does not meet the certainty threshold, select a further primary component prompt of the plurality of primary component prompts and instructing the multi-component system adjustment module to perform the above steps on the basis of the further primary component prompt; wherein the converter system further comprises a multi-component system converter module, comprising: a converter unit configured to generate a p

Abstract: A system and method implemented on a computing device for visualizing, exploring and examining various levels of supporting information details, by the computer accessing a corpus having a plurality of digital weighted conversation models of text-based interlocutory conversations, including annotations, paths, and weights; selecting a plurality of the conversations according to at least one annotation value at least one weight threshold; and generating a graphical user interface using the selected plurality of text-based interlocutory conversations, in which interlocutor Goals are depicted starting points in a flow-graph, interlocutor Turns are depicted as intermittent points in the flow-graph, and flow pipes are depicted between each interlocutor Goal and each Turn, to illustrate one or more text-based interlocutory conversations which traversed a flow from each goal to each Turn, in which each flow pipe is rendered with a width relative to other flow pipes in the flow graph according the weights.

Abstract: In one implementation, a computer-implemented method includes receiving, at a mobile computing device, ambiguous user input that indicates more than one of a plurality of commands; and determining a current context associated with the mobile computing device that indicates where the mobile computing device is currently located. The method can further include disambiguating the ambiguous user input by selecting a command from the plurality of commands based on the current context associated with the mobile computing device; and causing output associated with performance of the selected command to be provided by the mobile computing device.

Abstract: Pairing user devices includes receiving an indication of a group of co-located users, receiving information indicative of a topic of conversation of a subgroup of the co-located users, and determining a topic of the discussion using contextual analysis. One or more users of the subgroup of co-located users are identified. Each of the one or more users has a user device associated therewith. The one or more users is added to a communication group associated with the topic. A subset of the user devices for a pairing between the user devices are determined. The pairing between the subset of the user devices is initiated.

Abstract: Systems and processes for optimizing dialogue policy decisions for digital assistants using implicit feedback are provided. In an example process, a user utterance is received. Based on a text representation of the user utterance, one or more user intents corresponding to the user utterance are determined. A policy action is selected from a plurality of candidate policy actions based on a belief state for the one or more user intents and a policy model. The policy action is performed, including outputting results of the policy action for presentation. A success score for the policy action is determined based on whether one or more predetermined types of implicit user feedback are detected after performing the policy action. A set of parameter values of the policy model is modified using the determined success score.

Abstract: Procedures to identify the probabilities for different states in a vulnerability life cycle are described. The probabilities are used to develop a number of statistical models to evaluate the risk factor of a particular vulnerability at time “t”. A transition probability matrix of all states of a particular vulnerability as a function of time is also described. A Markov chain process can be iterated to reach a steady state of the transition probability matrix, with the initial probabilities reaching the absorbing states, including exploited and patched states. A risk factor is also introduced for use as an index of the risk of a vulnerability being exploited. Finally, statistical models that can calculate the risk factor more conveniently without going through the Markovian process are described.

Abstract: An online system predicts topics for content items. The online system provides one or more topic labels for a user to apply concurrently while a user is composing a post, in response to requests periodically received from the user's device. A request includes information such as content composed by the user and contextual information. The online system employs machine learning techniques to analyze content composed by a user and contextual information thereby to predict topic labels. Different machine learning models for classifying individual topic labels, identifying relevant topic labels, and/or detecting changes in existing topic predictions are developed. Some machine learning models predict topics for full content and some predict topics for partial content. The online system trains the machine learning models to ensure accurate topic predictions are provided timely. The online system employs various machine learning model training methods such as active training and gradient training.

Abstract: An internet question answering method is applied in an internet question answering system. A current-turn user question is received. Based on a discourse labeling model, a discourse of the current-turn user question is labeled as “discourse continue” or “discourse end” online and real-time. Based on the discourse of the current-turn user question, whether to clear at least one discourse of an old boundary is determined. The internet question answering system answers the current-turn user question. A match degree between a next-turn user question and the segment of the dialog log is compared to determine whether the discourse of the current-turn user question is correct, whether to correct the discourse of the current-turn user question, and whether to adjust the discourse labeling model by using the current-turn user question.

Abstract: An exemplary method for using a virtual assistant may include, at an electronic device configured to transmit and receive data, receiving a user request for a service from a virtual assistant; determining at least one task to perform in response to the user request; estimating at least one performance characteristic for completion of the at least one task with the electronic device, based on at least one heuristic; based on the estimating, determining whether to execute the at least one task at the electronic device; in accordance with a determination to execute the at least one task at the electronic device, causing the execution of the at least one task at the electronic device; in accordance with a determination to execute the at least one task outside the electronic device: generating executable code for carrying out the least one task; and transmitting the executable code from the electronic device.

Abstract: A statistical model for predicting an expected path length (“EPL”) of the steps of an attacker is described. The model is based on utilizing vulnerability information along with an attack graph. Using the model, it is possible to identify the interaction among vulnerabilities and individual variables or risk factors that drive the EPL. Gaining a better understanding of the relationship between the vulnerabilities and their interactions can provide security administrators with a better view and understanding of their security status. In addition, a number of different attributable variables and their contribution in estimating the EPL can be ranked. Thus, it is possible to utilize the ranking process to take precautions and actions to minimize the EPL.

Abstract: According to the embodiments, a statistical model is developed to estimate the probability of being in a certain stage of a particular vulnerability in its life cycle. The methodology with the application of Markov chain theory gives the basis for calculating estimates for probabilities for different stages of a life cycle of the vulnerability considered. Using the developed method, it is possible to evaluate the risk level of a particular vulnerability at a certain time. These developments allow an advantage in taking measures to avoid exploitations and introduce patches for the vulnerability before an attacker takes the advantage of that particular vulnerability.

Abstract: A dialogue system including: an input receiving data relating to a speech or text signal originating from a user; and a processor configured to: update a system state based on the input data using a state tracker model, the system state including probability values associated with each of plural possible values for each of plural categories; identify one or more relevant categories based on at least part of the updated system state information using an identifier model; define a set of information from stored information including plural action functions and categories, excluding categories not identified as relevant; generate a reduced system state, including the probability values associated with one or more of the plural possible values for each relevant category; determine an action based on the reduced system state and the set of information using a policy model; output information specified by the determined action at an output.

Abstract: Embodiments of the present invention provide a method, system and computer program product for telephonic fraud prevention. In an embodiment of the invention, a method of telephonic fraud prevention includes speech recognizing in real-time, audio of a telephone call from a caller to a called party. Once the real-time audio has been speech recognized into text, the text may be parsed into words and the words compared to a hierarchical semantic tree of terms. On the condition that a match is detected between one of the words and a node of the tree, a level of the tree is identified at which the match is detected and the level is correlated to a degree of risk of the telephone call. Finally, an alert is displayed to the called party reflecting the degree of risk.

Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.

Abstract: Methods and systems for a transportation vehicle are provided. One method includes receiving a user input for a valid communication session by a processor executable, digital assistant at a device on a transportation vehicle; tagging by the digital assistant, the user input words with a grammatical connotation; generating an action context, a filter context and a response context by a neural network, based on the tagged user input; storing by the digital assistant, a key-value pair for a parameter of the filter context at a short term memory, based on an output from the neural network; updating by the digital assistant, the key-value pair at the short term memory after receiving a reply to a follow-up request and another output from the trained neural network; and providing a response to the reply by the digital assistant.

Abstract: Described is a system for decoding recorded signals into movement commands of a prosthetic device. Using a biomechanical model and physical action data, biological signal data is related to kinetic data. The physical action data can include position, joint angle, speed, and acceleration of a part of a limb. The biological signal data can include recorded neural signals and recorded muscle signals. The kinetic data can include force, power, torque, and stress. Based on the relationship between the biological signal data and the kinetic data, control commands are generated to achieve an intended position and/or movement of a prosthesis.

Abstract: Described herein are systems and methods for two-stage training of a spoken dialog system. The first stage trains a policy network using external data to produce a semi-trained policy network. The external data includes one or more known fixed dialogs. The second stage trains the semi-trained policy network through interaction to produce a trained policy network. The interaction may be interaction with a user simulator.

Abstract: The present invention relates to a method and apparatus for exploiting human feedback in an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes inferring an intent from data entered by the human user, formulating a response in accordance with the intent, receiving feedback from a human advisor in response to at least one of the inferring and the formulating, wherein the human advisor is a person other than the human user, and adapting at least one model used in at least one of the inferring and the formulating, wherein the adapting is based on the feedback.

Abstract: The application relates to a hearing device comprising a) an input unit for delivering a time varying electric input signal representing an audio signal comprising at least two sound sources, b) a cyclic analysis buffer unit of length A adapted for storing the last A audio samples, c) a cyclic synthesis buffer unit of length, where L is smaller than A, adapted for storing the last L audio samples, which are intended to be separated in individual sound sources, d) a database having stored recorded sound examples from said at least two sound sources, each entry in the database being termed an atom, the atoms originating from audio samples from first and second buffers corresponding in size to said synthesis and analysis buffer units, where for each atom, the audio samples from the first buffer overlaps with the audio samples from the second buffer, and where atoms originating from the first buffer constitute a reconstruction dictionary, and where atoms originating from the second buffer constitute an analysis d

Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.

Abstract: A method for converting speech using phonetic posteriorgrams (PPGs). A target speech is obtained and a PPG is generated based on acoustic features of the target speech. Generating the PPG may include using a speaker-independent automatic speech recognition (SI-ASR) system for equalizing different speakers. The PPG includes a set of values corresponding to a range of times and a range of phonetic classes, the phonetic classes corresponding to senones. A mapping between the PPG and one or more segments of the target speech is generated. A source speech is obtained, and the source speech is converted into a converted speech based on the PPG and the mapping.

Abstract: Systems, methods, and devices for generating text-to-speech output using previously captured speech are described. Spoken audio is obtained and undergoes speech processing to create text. The resulting text is stored with the spoken audio, with both the text and the spoken audio being associated with the individual that spoke the audio. Various spoken audio and corresponding text are stored over time to create a library of speech units. When the individual sends a text message to a recipient, the text message is processed to determine portions of text, and the portions of text are compared to the library of text associated with the individual. When text in the library is identified, the system selects the spoken audio units associated with the identified stored text. The selected spoken audio units are then used to generate output audio data corresponding to the original text message, with the output audio data being sent to a device of the message recipient.

Abstract: A frame erasure concealment technique for a bitstream-based feature extractors in a speech recognition system particularly suited for use in a wireless communication system operates to “delete” each frame in which an erasure is declared. The deletions thus reduce the length of the observation sequence, but have been found to provide for sufficient speech recognition based on both single word and “string” tests of the deletion technique.

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: A state estimating apparatus includes: a spectrum calculating unit which calculates a power spectrum for each of a plurality of frequencies on a frame-by-frame basis from a voice signal containing voice of a first speaker and voice of a second speaker transmitted over a telephone line; a band power calculating unit which calculates power of a non-transmission band on a frame-by-frame basis, based on the power spectra of frequencies contained in the non-transmission band among the plurality of frequencies; a transmitted-voice judging unit which determines that any frame whose power in the non-transmission band is greater than a threshold value indicating the presence of voice carries the voice of the first speaker; and a state judging unit which judges whether the state of mind of the first speaker is normal or abnormal, based on the frame judged to carry the voice of the first speaker.

Abstract: According to some embodiments of the present invention there is provided a computerized method for speech processing using a Gaussian Mixture Model. The method comprises the action of receiving by hardware processor(s) two or more covariance values representing relationships between distributions of speech coefficient values that represent two or more audible input speech signals recorded by a microphone. The method comprises the action of computing two or more eigenvectors and eignevalues using a principle component analysis of the covariance values and transforming the speech coefficient values using the eigenvectors and computing two or more second covariance values from the transformed speech coefficient values. The method comprises the action of modifying some of the second covariance values according to the eignevalues, the covariance values, and two or more indices of the speech coefficient values. The second covariance values to the speech processor comprising the Gaussian Mixture Model.

Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.

Abstract: In some embodiments, a system is provided comprising at least one processor programmed to process an input text to identify a plurality of semantic patterns that match the input text, wherein, for at least one semantic pattern of the plurality of semantic patterns: the at least one semantic pattern comprises a plurality of semantic entities identified from the at least one input text, and the plurality of semantic entities occur in a common context within the at least one input text. The at least one processor may be further programmed to use statistical information derived from training data to associate a respective weight with each semantic pattern of the plurality of semantic patterns.

Abstract: Methods, devices, and computer program products for recognizing and responding to natural language input are described herein. Natural language input is received at a natural language input interface of a computing device and transformed into computer-usable text. A natural language input recognizer obtains evidence from one or more evidence source and generates an evidence graph based on the evidence obtained. Evidence may be obtained asynchronously, and the natural language input recognizer may update the evidence graph upon receipt of additional evidence. The natural language input recognizer generates a set of recognition hypotheses based on the evidence graph and selects one of the recognition hypotheses as a recognition result for the natural language input. Semantic models, evidence models, and response models may be employed to generate the evidence graph and respond to the recognition result selected for the natural language input.

Abstract: A network reliability evaluation method for an acyclic network and a system thereof are provided. The network reliability evaluation method searches all minimal paths from a source node to a sink source based on nodes according to the properties of the acyclic network. In conventional network reliability evaluation methods, searching all minimal paths is based on arcs. Therefore, the network reliability evaluation method and the system thereof can effectively reduce the complexity of calculation.

Abstract: A controller for a dialog manager, the dialog manager being configured to receive a representation of an input utterance from a user and control the flow of conversation with the user. The controller is configured to implement a parameterized policy for defining the behavior of a dialog manager. The parameterized policy is configured to operate with an ontology-independent parameter as an input. The controller has a processor for parameterizing an end user ontology such that the parameterized policy can define the behavior of a dialog manager for the end user ontology. The processor is configured to define a slot of the end user ontology in terms of at least one of the ontology-independent parameters such that it is suitable for being used as an input to the parameterized policy.