Abstract: A verbal description method and system. A computing system broadcasts first audio data and video data associated with the first audio data. The computing system determines that the video data comprises a graphic without a description in the first audio data. The computing system receives audible description data associated with the graphic. The computing system generates second audio data comprising the first audio data and the audible description data. The computing system synchronizes portions of the second audio data with associated portions of the video data. The computing system generates synchronized audio/video data comprising the portions of said second audio data aligned with the associated portions of said video data. The computing system broadcasts the synchronized audio/video data.

Abstract: Techniques for conversion of non-back-off language models for use in speech decoders. For example, an apparatus for conversion of non-back-off language models for use in speech decoders. For example, an apparatus is configured convert a non-back-off language model to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

Abstract: Techniques for conversion of non-back-off language models for use in speech decoders. For example, a method comprises the following step. A non-back-off language model is converted to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

Abstract: A method, information processing system, and computer readable article of manufacture model data. A first dataset is received that includes a first set of physical world data. At least one data model associated with the first dataset is generated based on the receiving. A second dataset is received that includes a second set of physical world data. The second dataset is compared to the at least one data model. A probability that the second dataset is modeled by the at least one data model is determined. A determination is made that the probability is above a given threshold. A decision associated with the second dataset based on the at least one data model is generated in response to the probability being above the given threshold. The probability and the decision are stored in memory. The probability and the decision are provided to user via a user interface.

Abstract: A method for eliminating typing noise from a conference call in which a plurality of participants communicate via a plurality of client devices connected to a conference server via a corresponding plurality of channels, includes determining a probability value for each channel of the plurality of channels representing a likelihood of a typing noise being present on the corresponding channel. A channel of the plurality of channels having a highest determined probability value is temporarily muted. It is testing whether the temporary muting has successfully remove the typing noise from the conference call. A warning is generated for a client device of the plurality of client devices that corresponds to the channel having a highest determined probability value when it is determined that the temporary muting has successfully removed the typing noise from the conference call.

Abstract: A method of identifying and using side information available to statistical machine translation systems within an enterprise setting, the method including extracting user-specific interaction and non-interaction-based information from at least one corresponding database within the enterprise for each of a plurality of users, aggregating the user-specific interaction and non-interaction based information from a plurality of users, by using a processor on a computer, to tune and adapt background translation and language models, and updating all relevant models within the enterprise after user activity based on the tuned and adapted translation and language models.

Abstract: Pretraining for a DBN initializes weights of the DBN (Deep Belief Network) using a hybrid pre-training methodology. Hybrid pre-training employs generative component that allows the hybrid PT method to have better performance in WER (Word Error Rate) compared to the discriminative PT method. Hybrid pre-training learns weights which are more closely linked to the final objective function, allowing for a much larger batch size compared to generative PT, which allows for improvements in speed; and a larger batch size allows for parallelization of the gradient computation, speeding up training further.

Abstract: A method for eliminating typing noise from a conference call in which a plurality of participants communicate via a plurality of client devices connected to a conference server via a corresponding plurality of channels, includes determining a probability value for each channel of the plurality of channels representing a likelihood of a typing noise being present on the corresponding channel. A channel of the plurality of channels having a highest determined probability value is temporarily muted. It is testing whether the temporary muting has successfully remove the typing noise from the conference call. A warning is generated for a client device of the plurality of client devices that corresponds to the channel having a highest determined probability value when it is determined that the temporary muting has successfully removed the typing noise from the conference call.

Abstract: Deep belief networks are usually associated with a large number of parameters and high computational complexity. The large number of parameters results in a long and computationally consuming training phase. According to at least one example embodiment, low-rank matrix factorization is used to approximate at least a first set of parameters, associated with an output layer, with a second and a third set of parameters. The total number of parameters in the second and third sets of parameters is smaller than the number of sets of parameters in the first set. An architecture of a resulting artificial neural network, when employing low-rank matrix factorization, may be characterized with a low-rank layer, not employing activation function(s), and defined by a relatively small number of nodes and the second set of parameters. By using low rank matrix factorization, training is faster, leading to rapid deployment of the respective system.

Abstract: Techniques disclosed herein include systems and methods for voice-enabled searching. Techniques include a co-occurrence based approach to improve accuracy of the 1-best hypothesis for non-phrase voice queries, as well as for phrased voice queries. A co-occurrence model is used in addition to a statistical natural language model and acoustic model to recognize spoken queries, such as spoken queries for searching a search engine. Given an utterance and an associated list of automated speech recognition n-best hypotheses, the system rescores the different hypotheses using co-occurrence information. For each hypothesis, the system estimates a frequency of co-occurrence within web documents. Combined scores from a speech recognizer and a co-occurrence engine can be combined to select a best hypothesis with a lower word error rate.

Abstract: A method for eliminating typing noise from a conference call in which a plurality of participants communicate via a plurality of client devices connected to a conference server via a corresponding plurality of channels, includes determining a probability value for each channel of the plurality of channels representing a likelihood of a typing noise being present on the corresponding channel. A channel of the plurality of channels having a highest determined probability value is temporarily muted. It is testing whether the temporary muting has successfully remove the typing noise from the conference call. A warning is generated for a client device of the plurality of client devices that corresponds to the channel having a highest determined probability value when it is determined that the temporary muting has successfully removed the typing noise from the conference call.

Abstract: A method for eliminating typing noise from a conference call in which a plurality of participants communicate via a plurality of client devices connected to a conference server via a corresponding plurality of channels, includes determining a probability value for each channel of the plurality of channels representing a likelihood of a typing noise being present on the corresponding channel. A channel of the plurality of channels having a highest determined probability value is temporarily muted. It is testing whether the temporary muting has successfully remove the typing noise from the conference call. A warning is generated for a client device of the plurality of client devices that corresponds to the channel having a highest determined probability value when it is determined that the temporary muting has successfully removed the typing noise from the conference call.

Abstract: Methods and apparatus for language translation in a computing environment associated with a virtual application are presented. For example, a method for providing language translation includes determining languages of a user and a correspondent; determining one or more sequences of translators; determining a selected sequence of selected translators from the one or more sequences of the translators; requesting a change in virtual locations, within the computing environment associated with the virtual application, of one or more selected translator virtual representations of the selected translators to a virtual meeting location within the computing environment associated with the virtual application; and changing virtual locations of the one or more selected translator virtual representations to the virtual meeting location.

Abstract: Methods and apparatus for language translation in a computing environment associated with a virtual application are presented. For example, a method for providing language translation includes determining languages of a user and a correspondent; determining one or more sequences of translators; determining a selected sequence of selected translators from the one or more sequences of the translators; requesting a change in virtual locations, within the computing environment associated with the virtual application, of one or more selected translator virtual representations of the selected translators to a virtual meeting location within the computing environment associated with the virtual application; and changing virtual locations of the one or more selected translator virtual representations to the virtual meeting location.

Abstract: Techniques disclosed herein include systems and methods for voice-enabled searching. Techniques include a co-occurrence based approach to improve accuracy of the 1-best hypothesis for non-phrase voice queries, as well as for phrased voice queries. A co-occurrence model is used in addition to a statistical natural language model and acoustic model to recognize spoken queries, such as spoken queries for searching a search engine. Given an utterance and an associated list of automated speech recognition n-best hypotheses, the system rescores the different hypotheses using co-occurrence information. For each hypothesis, the system estimates a frequency of co-occurrence within web documents. Combined scores from a speech recognizer and a co-occurrence engine can be combined to select a best hypothesis with a lower word error rate.

Abstract: A multiple audio/video data stream simulation method and system. A computing system receives first audio and/or video data streams. The first audio and/or video data streams include data associated with a first person and a second person. The computing system monitors the first audio and/or video data streams. The computing system identifies emotional attributes comprised by the first audio and/or video data streams. The computing system generates second audio and/or video data streams associated with the first audio and/or video data streams. The second audio and/or video data streams include the first audio and/or video data streams data without the emotional attributes. The computing system stores the second audio and/or video data streams.

Abstract: Some aspects include transforming data, at least a portion of which has been processed to determine frequency information associated with features in the data. Techniques include determining a first transformation based, at least in part, on the frequency information, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.

Abstract: Some aspects include transforming data, at least a portion of which has been processed to determine at least one representative vector associated with each of a plurality of classifications associated with the data to obtain a plurality of representative vectors. Techniques comprise determining a first transformation based, at least in part, on the plurality of representative vectors, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.

Abstract: Some aspects include transforming data for which at least one constraint has been specified on a portion of the data, the at least one constraint relating to a similarity and/or dissimilarity of at least some of the portion of the data. Techniques comprise determining a first transformation that approximates the at least one constraint using a cosine similarity as a measure of the similarity and/or dissimilarity of the at least a portion of the data, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.

Abstract: A sparse representation method of text classification is described. An input text document is represented as a document feature vector y. A category dictionary H provides possible examples [h1; h2; . . . ; hn] of the document feature vector y. The input text document is classified using a sparse representation text classification algorithm that solves for y=H? where a sparseness condition is enforced on ? to select a small number of examples from the dictionary H to describe the document feature vector y.