Abstract: A system and method are described for generating semantically similar sentences for a statistical language model. A semantic class generator determines for each word in an input utterance a set of corresponding semantically similar words. A sentence generator computes a set of candidate sentences each containing at most one member from each set of semantically similar words. A sentence verifier grammatically tests each candidate sentence to determine a set of grammatically correct sentences semantically similar to the input utterance. Also note that the generated semantically similar sentences are not restricted to be selected from an existing sentence database.

Abstract: An apparatus, a system, and a method for transferring data from a terminal to an Electromyography (EMG) device are provided. The method includes detecting a user motion, determining whether the user motion corresponds to a motion associated with requesting data to be transferred from the source terminal to the EMG device, and if the user motion corresponds to a motion associated with requesting data to be transferred to from the source terminal to the EMG device, transmitting to the source terminal a request for the data according to the user motion.

Abstract: An apparatus and method for selecting items on a portable terminal are provided. The method includes receiving an input for rearranging at least one item on a User Interface (UI), and rearranging and displaying on a screen the at least one item on the UI. The at least one rearranged item is rearranged so as to be displayed in a position that is different from an original position of the at least one rearranged item in relation to a remaining portion of the UI.

Abstract: Labeling a call, for instance by identifying an intent (i.e., the reason why the caller has called into the call center), of a caller in a conversation between a caller and an agent is a useful task for efficient customer relationship management (CRM). In an embodiment, a method of labeling sentences for presentation to a human can include selecting an intent bearing excerpt from sentences, presenting the intent bearing excerpt to the human, and enabling the human to apply a label to each sentence based on the presentation of the intent bearing excerpt. The method can reduce a manual labeling budget while increasing the accuracy of labeling models based on manual labeling.

Abstract: Methods, systems, and computer program products for identifying one or more utterances that are likely to carry the intent of a speaker are provided herein. A method includes providing a transcript of utterances to a word weight scoring module to perform inverse document frequency based scoring on each word in the transcript, thereby generating a weight for each word; calculating a weight for each utterance in the transcript to generate weighted utterances by summing the weights or each constituent word in each utterance; comparing at least one weighted utterance to pre-existing to example utterances carrying the intent of a speaker to determine a relevancy score for the at least one weighted utterance; and generating a ranked order of the at least one weighted utterance from highest to lowest intent relevancy score, wherein the highest intent relevancy score corresponds to the utterance which is most likely to carry intent of the speaker.

Abstract: Techniques, an apparatus and an article of manufacture identifying one or more utterances that are likely to carry the intent of a speaker, from a conversation between two or more parties. A method includes obtaining an input of a set of utterances in chronological order from a conversation between two or more parties, computing an intent confidence value of each utterance by summing intent confidence scores from each of the constituent words of the utterance, wherein intent confidence scores capture each word's influence on the subsequent utterances in the conversation based on (i) the uniqueness of the word in the conversation and (ii) the number of times the word subsequently occurs in the conversation, and generating a ranked order of the utterances from highest to lowest intent confidence value, wherein the highest intent value corresponds to the utterance which is most likely to carry intent of the speaker.

Abstract: Identification of an intent of a conversation can be useful for real-time or post-processing purposes. According to example embodiments, a method, and corresponding apparatus of identifying at least one intent-bearing utterance in a conversation, comprises determining at least one feature for each utterance among a subset of utterances of the conversation; classifying each utterance among the subset of utterances, using a classifier, as an intent classification or a non-intent classification based at least in part on a subset of the at least one determined feature; and selecting at least one utterance, with intent classification, as an intent-bearing utterance based at least in part on classification results by the classifier. Through identification of an intent bearing utterance, a call center for example, can provide improved service for callers through, for example, more effective directing of a call to a live agent.

Abstract: Determining synonyms of words in a set of documents. Particularly, when provided with a word or phrase as input, in exemplary embodiments there is afforded the return of a predetermined number of “top” synonym words (or phrases) for an input word (or phrase) in a specific collection of text documents. Further, a user is able to provide ongoing and iterative positive or negative feedback on the returned synonym words, by manually accepting or rejecting such words as the process is underway.

Abstract: Methods and arrangements for executing an audio search. A search query in a first language variety is accepted, the search query being in a form of at least one of: text and audio. A corpus of material in the first language variety is accessed, and first language variety baseforms are obtained via data obtained from a second language variety. A first language variety phonetic model is built, and the first language variety phonetic model and the second language variety are employed in executing an audio search based on the accepted search query.

Abstract: Methods and arrangements for executing an audio search. A search query in a first language variety is accepted, the search query being in a form of at least one of: text and audio. A corpus of material in the first language variety is accessed, and first language variety baseforms are obtained via data obtained from a second language variety. A first language variety phonetic model is built, and the first language variety phonetic model and the second language variety are employed in executing an audio search based on the accepted search query.

Abstract: Techniques, systems, and articles of manufacture for determining the current logical state of a social media communication thread. A method includes computing an initial probability for applicability of each of multiple logical states for a first entry in a social media communication thread, wherein each logical state corresponds to a stage of interaction between customers of an enterprise and/or agents of the enterprise based on features derived from content of entries in the communication thread, network structure of entries, and identity of authors of entries, computing a transition probability between each subsequent consecutive entry in the communication thread, wherein the transition probability indicates the probability of moving from one logical state to another, and determining the current logical state of the communication thread based on the computed initial probability for the first entry and the computed transition probability between each subsequent entry in the communication thread.

Abstract: Techniques for evaluating one or more spoken language skills of a speaker are provided. The techniques include identifying one or more temporal locations of interest in a speech passage spoken by a speaker, computing one or more acoustic parameters, wherein the one or more acoustic parameters capture one or more properties of one or more acoustic-phonetic features of the one or more locations of interest, and combining the one or more acoustic parameters with an output of an automatic speech recognizer to modify an output of a spoken language skill evaluation.

Abstract: In accordance with an embodiment of the invention, there is provided a technique for permitting a machine to discover classes and topics that data contains and to annotate data objects with those identified classes. The technique enables machines to group and annotate data objects in ways that are meaningful and intuitive for a user of the data objects. An interactive method uses clustering, along with feedback from a user on the clustering output, to discover a set of classes. The feedback from the user is used to guide the clustering process in the later stages, which results in better and better discovery of classes and annotation with more and more human feedback. A method can be used to produce labeled data that involves discovering classes and annotating a given dataset with the discovered class labels. This is advantageous for building a classifier that has wide applications, such as call routing and intent discovery.

Abstract: A phonetic vocabulary for a speech recognition system is adapted to a particular speaker's pronunciation. A speaker can be attributed specific pronunciation styles, which can be identified from specific pronunciation examples. Consequently, a phonetic vocabulary can be reduced in size, which can improve recognition accuracy and recognition speed.

Abstract: A method and system for evaluating cross-domain clusterability upon a target domain and a source domain. Target clusterability is calculated as an average of a respective clusterability of at least one target data item comprised by the target domain. Target-side matchability is calculated as an average of a respective matchability of each target centroid of the target domain to source centroids of the source domain, wherein the source domain comprises at least one source data item. Source-side matchability is calculated as an average of a respective matchability of each source centroid of said source centroids to the target centroids. Source-target pair matchability is calculated as an average of the target-side matchability and the source-side matchability. Cross-domain clusterability between the target domain and the source domain is calculated as a linear combination of the calculated target clusterability and the calculated source-target pair matchability.

Abstract: A method, an apparatus and an article of manufacture for automatic speech recognition. The method includes obtaining at least one language model word and at least one rule-based grammar word, determining an acoustic similarity of at least one pair of language model word and rule-based grammar word, and increasing a transition cost to the at least one language model word based on the acoustic similarity of the at least one language model word with the at least one rule-based grammar word to generate a modified language model for automatic speech recognition.

Abstract: A process for evaluating cross-domain clusterability upon a target domain and a source domain. The cross-domain clusterability is calculated as a linear combination of a target clusterability and a source-target pair matchability, by use of a trade-off parameter that determines relative contribution of the target clusterability and the source-target pair matchability. The target clusterability quantifies how clusterable the target domain is. The source-target pair matchability is calculated as an average of a target-side matchability and a source-side matchability, which quantifies how well target centroids of the target domain are aligned with the source centroids and how well source centroids of the source domain are aligned with the target centroids, respectively.

Abstract: A computer system for evaluating cross-domain clusterability upon a target domain and a source domain. The cross-domain clusterability is calculated as a linear combination of a target clusterability and a source-target pair matchability, by use of a trade-off parameter that determines relative contribution of the target clusterability and the source-target pair matchability. The target clusterability quantifies how clusterable the target domain is. The source-target pair matchability is calculated as an average of a target-side matchability and a source-side matchability, which quantifies how well target centroids of the target domain are aligned with the source centroids and how well source centroids of the source domain are aligned with the target centroids, respectively.

Abstract: A computer program product evaluating cross-domain clusterability upon a target domain and a source domain. The cross-domain clusterability is calculated as a linear combination of a target clusterability and a source-target pair matchability, by use of a trade-off parameter that determines relative contribution of the target clusterability and the source-target pair matchability. The target clusterability quantifies how clusterable the target domain is. The source-target pair matchability is calculated as an average of a target-side matchability and a source-side matchability, which quantifies how well target centroids of the target domain are aligned with the source centroids and how well source centroids of the source domain are aligned with the target centroids, respectively.

Abstract: Techniques, an apparatus and an article of manufacture identifying one or more utterances that are likely to carry the intent of a speaker, from a conversation between two or more parties. A method includes obtaining an input of a set of utterances in chronological order from a conversation between two or more parties, computing an intent confidence value of each utterance by summing intent confidence scores from each of the constituent words of the utterance, wherein intent confidence scores capture each word's influence on the subsequent utterances in the conversation based on (i) the uniqueness of the word in the conversation and (ii) the number of times the word subsequently occurs in the conversation, and generating a ranked order of the utterances from highest to lowest intent confidence value, wherein the highest intent value corresponds to the utterance which is most likely to carry intent of the speaker.