Abstract: A method and apparatus for outputting information are provided. A specific embodiment of the method comprises: retrieving at least one medical entity keyword and at least one attribute keyword from a target medical text; then generating a set of keyword pairs, each of the keyword pairs including the retrieved medical entity keyword and the retrieved attribute keyword; then retrieving, for each of the keyword pairs in the set of keyword pairs, a text characteristic of the each of the keyword pairs in the target medical text, and introducing the retrieved text characteristic into a pre-trained association-relationship determination model to obtain an association result corresponding to the each of the keyword pairs; and finally outputting the keyword pairs having the association relationship in the set of keyword pairs. The embodiment improves the abundance of outputted information contents.

Abstract: This disclosure relates generally to quality evaluation of collaborative text input, and more particularly to system and method for quality evaluation of collaborative text inputs using Long Short Term Memory (LSTM) networks. In one embodiment, the method includes receiving an input data associated with a task to be accomplished collaboratively and sequentially by a plurality of contributors. The input data includes task-wise data sequence of contributor's post-edit submissions. A plurality of features are extracted from the input data. Based on the plurality of features, a plurality of input sequences are constructed. The input sequences include a plurality of concatenated feature vectors, where each of the concatenated feature vectors includes a post-edit feature vector and a contributor representation feature vector. The input sequences are modelled as a LSTM network, where the LSTM network is utilized to train a binary classifier for quality evaluation of the post-edit submission.

Abstract: Word vectors are multi-dimensional vectors that represent words in a corpus of text and that are embedded in a semantically-encoded vector space; paragraph vectors extend word vectors to represent, in the same semantically-encoded space, the overall semantic content and context of a phrase, sentence, paragraph, or other multi-word sample of text. Word and paragraph vectors can be used for sentiment analysis, comparison of the topic or content of samples of text, or other natural language processing tasks. However, the generation of word and paragraph vectors can be computationally expensive. Accordingly, word and paragraph vectors can be determined only for user-specified subsets of fields of incident reports in a database.

Abstract: Exemplary embodiments relate to detecting, removing, and/or replacing objectionable words and phrases in a machine-generated translation. A classifier identifies translations containing target words or phrases. The classifier may be applied to the output translation to remove target words and phrases from the translation, or to prevent target words and phrases from being automatically presented. Further, the classifier may be applied to a translation model to prevent the target words and phrases from appearing in the output translation. Still further, the classifier may be applied to training data so that the translation model is not trained using the target words of phrases. The classifier may remove target words or phrases only when the target words or phrases appear in the output translation but not the source language input data. The classifier may be provided as a standalone service, or may be employed in the context of a machine translation system.

Abstract: Disclosed is a voice recognition device (10) including: a voice recognition unit (11) for recognizing a user's uttered voice; a function performing unit (12) for performing a function corresponding to a recognition result provided by the voice recognition unit (11); a performance degree calculating unit (13) for calculating a degree to which the function performing unit (12) can perform the function corresponding to the recognition result; and a control unit (15) for, when the degree calculated by the performance degree calculating unit (13) is equal to or greater than a predetermined first reference, causing the function performing unit (12) to perform the function corresponding to the recognition result.

Abstract: A document processing system is configured to identify, for each accessed electronic document in a first set of multiple electronic documents, a set of identified multi-word phrases determined to be in ordered text information in the accessed electronic document, each multi-word phrase of the set of identified multi-word phrases including adjacent words in the ordered text information; and determine, for each accessed electronic document in the first set of multiple electronic documents, a selected document type from the first set of document types based at least on an analysis of the set of identified multi-word phrases with respect to multi-word-phrase characteristics identified by a first definition and associated with each document type in a first set of document types associated with a first document-set type.

Abstract: An apparatus, system and method of providing an artificially intelligent (AI) agent capable of assisting information technology (IT) personnel in addressing an IT ticket. The AI agent may include a visualization interface for display capable of receiving dialog from the IT personnel related to the IT ticket; a translation module capable of translating the received dialog to at least one machine language translation; a solutions module capable of receiving the machine language translation, comparing the machine language to a plurality of prospective solutions for IT issues, and selecting a subset of the plurality of prospective solutions deemed most relevant to the IT ticket and returning that subset to the visualization interface; and a feedback module capable of receiving explicit and implied feedback from the IT personal regarding the machine language translation and the selected subset, wherein the selecting of the subset varies upon subsequent received dialog according to the feedback.

Abstract: A speech recognition system comprises: an input, for receiving an input signal from at least one microphone; a first buffer, for storing the input signal; a noise reduction block, for receiving the input signal and generating a noise reduced input signal; a speech recognition engine, for receiving either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block; and a selection circuit for directing either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block to the speech recognition engine.

Abstract: A sampled speech data sequence contains words spoken by a speaker. A sequence of feature vectors is generated characterizing spectral distribution of sampled speech data. A textual transcript of the words spoken by the speaker is obtained. Data structures of a universal background model of a Gaussian mixture model (UBM-GMM) and of an Enrolled speaker Gaussian mixture model (ENR-GMM) are adapted responsive to the textual transcript, to generate an adapted UBM-GMM and an adapted ENR-GMM, respectively. An enrolled speaker probability is generated based on the sequence of feature vectors and the adapted ENR-GMM, and a universal speaker probability is generated based on the sequence of feature vectors and the adapted UBM-GMM. A speaker verification indication of whether the speaker is an enrolled speaker is generated by comparing the enrolled speaker probability to the universal speaker probability.

Abstract: The present invention extends to methods, systems, and computer program products for detecting an event. A listening area is monitored based on detecting a potential event from a normalized signal, based on characteristics of a normalized signal, or based on a signal pattern anomaly. A geo cell database is queried with search terms derived from one or more normalized signals. A geo cell subset is returned from the geo cell database. The listening area is formed from the geo cells included in the geo cell subset and monitored for additional signals. An event is detected and/or validated (or rejected) based on the additional normalized signal.

Abstract: A computer-implemented method for determining contextual relevance in multi-auditory source scenarios is disclosed, the method including receiving, by a cognitive system, auditory communications regarding a current activity, analyzing, by the cognitive system, each auditory communication to determine an intended action. For each intended action, the cognitive system creates a simulation to identify a resulting outcome of each intended action. The method further includes ranking, by the cognitive system, the resulting outcome, the ranking based on a comparison of each simulated result and the corresponding intended action regarding the current activity, and physically implementing the highest rated resulting outcome(s) for the current activity. The analyzing, in one example, includes assigning a weight to each of the relevant auditory communications based on one or more criterion, and ranking the relevant auditory communications by weight.

Abstract: The present disclosure generally relates to using voice interaction to access call functionality of a companion device. In an example process, a user utterance is received. Based on the user utterance and contextual information, the process causes a server to determine a user intent corresponding to the user utterance. The contextual information is based on a signal received from the companion device. In accordance with the user intent corresponding to an actionable intent of answering the incoming call, a command is received. Based on the command, instructions are provided to the companion device, which cause the companion device to answer the incoming call and provide audio data of the answered incoming call. Audio is outputted according to the audio data of the answered incoming call.

Abstract: The present disclosure discloses a method and apparatus for providing a voice service. A specific implementation of the method for providing a voice service comprises: acquiring a voice input signal; analyzing the time-domain waveform of the voice input signal to determine current speed information of the voice input signal; comparing the current speed information with an acquired standard speed information set of a user outputting the voice input signal, and determining first demand information from a preset demand information set according to the comparison result, wherein the standard speed information set comprises at least one piece of standard speed information, and the preset demand information set comprises demand information corresponding to each piece of standard speed information in the standard speed information set; and generating a voice response signal based on the first demand information and the second demand information acquired by analyzing the voice input signal.

Abstract: Feedback mechanisms to the user of a Head Mounted Display (HMD) are provided. It is important to provide feedback to the user when speech is recognized as soon as possible after the user utters a voice command. The HMD displays and/or audibly renders an ASR acknowledgment in a manner that ensures the user that the HMD has received/understood his voiced command.

Abstract: Systems and methods for provisioning optimized resources in a cloud environment are described. The system receives voice-based user input for accessing resources in the cloud environment. The voice input is converted into textual data from which one or more keywords are identified. Further, the system automatically determine one or more parameters and corresponding one or more values of the one or more parameters required for accessing the resources based on the one or more keywords. These one or more values are populated in one or more fields corresponding to the one or more parameters. The one or more values indicates an optimal machine configuration of the resource. Further, the system provisions the optimized resource based on the populating of the one or more values in the one or more fields.

Abstract: The present invention relates to a method and an apparatus for encoding and decoding spectrum coefficients in the frequency domain. The spectrum encoding method may comprise the steps of: selecting an encoding type on the basis of bit allocation information of respective bands; performing zero encoding with respect to a zero band; and encoding information of selected significant frequency components with respect to respective non-zero bands. The spectrum encoding method enables encoding and decoding of spectrum coefficients which is adaptive to various bit-rates and various sub-band sizes. In addition, a spectrum can be encoded using a TCQ method at a fixed bit rate using a bit-rate control module in a codec that supports multiple rates. Encoding performance of the codec can be maximised by encoding high performance TCQ at a precise target bit rate.

Abstract: This disclosure describes, in part, techniques for performing multi-path calculations for energy levels on an electronic device. For instance, the electronic device may include a first circuit and a second circuit, where the first circuit uses less power than the second circuit. As such, when operating in a standby mode, the electronic device may use the first circuit to calculate energy levels at the electronic device, such as speech-energy values and ambient-energy values. Additionally, while operating in an active mode, the electronic device may active the second circuit and then use the second circuit to calculate the energy levels at the electronic device. The first circuit and the second circuit can send/receive current energy levels between one another so that the electronic device can continually calculate the energy levels even when the electronic device switches between modes of operation.

Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.

Abstract: A method and apparatus for performing analysis on data collected at a point of sale is disclosed. The data from the point of sale is collected using voice recognition technique implemented on a mobile communication device. In order to enable this, a limited vocabulary word recognition technique is implemented using a set of libraries storing speech utterances in a memory storage unit present of the mobile communication device. Dynamic updating of module parameters associated with the stored speech utterances is enabled by a speech refinement unit of the mobile communication device. The device further enables local as well as regional data collation and analysis.

Abstract: Computer-implemented systems and methods for extracting information during a human-to-human mono-lingual or multi-lingual dialog between two speakers are disclosed. Information from either the recognized speech (or the translation thereof) by the second speaker and/or the recognized speech by the first speaker (or the translation thereof) is extracted. The extracted information is then entered into an electronic form stored in a data store.