Abstract: A computer-implemented method according to one embodiment includes estimating a speaker dependent acoustic model utilizing test speech data and maximum likelihood linear regression (MLLR), transforming labeled speech data to create transformed speech data, utilizing the speaker dependent acoustic model and a linear transformation, and adjusting a deep neural network (DNN) acoustic model, utilizing the transformed speech data.

Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.

Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.

Abstract: Aspects described herein are directed towards methods, computing devices, systems, and computer-readable media that apply scattering operations to extracted visual features of audiovisual input to generate predictions regarding the speech status of a subject. Visual scattering coefficients generated according to one or more aspects described herein may be used as input to a neural network operative to generate the predictions regarding the speech status of the subject. Predictions generated based on the visual features may be combined with predictions based on audio input associated with the visual features. In some embodiments, the extracted visual features may be combined with the audio input to generate a combined feature vector for use in generating predictions.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: According to some aspects, a method of classifying speech recognition results is provided, using a neural network comprising a plurality of interconnected network units, each network unit having one or more weight values, the method comprising using at least one computer, performing acts of providing a first vector as input to a first network layer comprising one or more network units of the neural network, transforming, by a first network unit of the one or more network units, the input vector to produce a plurality of values, the transformation being based at least in part on a plurality of weight values of the first network unit, sorting the plurality of values to produce a sorted plurality of values, and providing the sorted plurality of values as input to a second network layer of the neural network.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: Aspects described herein are directed towards methods, computing devices, systems, and computer-readable media that apply scattering operations to extracted visual features of audiovisual input to generate predictions regarding the speech status of a subject. Visual scattering coefficients generated according to one or more aspects described herein may be used as input to a neural network operative to generate the predictions regarding the speech status of the subject. Predictions generated based on the visual features may be combined with predictions based on audio input associated with the visual features. In some embodiments, the extracted visual features may be combined with the audio input to generate a combined feature vector for use in generating predictions.

Abstract: A method, executed by a computer, includes monitoring a conversation between a plurality of meeting participants, identifying a conversational focus within the conversation, generating at least one question corresponding to the conversational focus, and retrieving at least one answer corresponding to the at least one question. A computer system and computer program product corresponding to the method are also disclosed herein.

Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.

Abstract: Operation of an automated dialog system is described using a source language to conduct a real time human machine dialog process with a human user using a target language. A user query in the target language is received and automatically machine translated into the source language. An automated reply of the dialog process is then delivered to the user in the target language. If the dialog process reaches an initial assistance state, a first human agent using the source language is provided to interact in real time with the user in the target language by machine translation to continue the dialog process. Then if the dialog process reaches a further assistance state, a second human agent using the target language is provided to interact in real time with the user in the target language to continue the dialog process.

Abstract: Deep scattering spectral features are extracted from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal. The deep scattering spectral feature representation is input to a speech recognition engine. The acoustic input signal is decoded based on at least a portion of the deep scattering spectral feature representation input to a speech recognition engine.

Abstract: A method for training a deep neural network (DNN), comprises receiving and formatting speech data for the training, performing Hessian-free sequence training (HFST) on a first subset of a plurality of subsets of the speech data, and iteratively performing the HFST on successive subsets of the plurality of subsets of the speech data, wherein iteratively performing the HFST comprises reusing information from at least one previous iteration.

Abstract: Aspects described herein are directed towards methods, computing devices, systems, and computer-readable media that apply scattering operations to extracted visual features of audiovisual input to generate predictions regarding the speech status of a subject. Visual scattering coefficients generated according to one or more aspects described herein may be used as input to a neural network operative to generate the predictions regarding the speech status of the subject. Predictions generated based on the visual features may be combined with predictions based on audio input associated with the visual features. In some embodiments, the extracted visual features may be combined with the audio input to generate a combined feature vector for use in generating predictions.

Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.

Abstract: According to some aspects, a method of classifying speech recognition results is provided, using a neural network comprising a plurality of interconnected network units, each network unit having one or more weight values, the method comprising using at least one computer, performing acts of providing a first vector as input to a first network layer comprising one or more network units of the neural network, transforming, by a first network unit of the one or more network units, the input vector to produce a plurality of values, the transformation being based at least in part on a plurality of weight values of the first network unit, sorting the plurality of values to produce a sorted plurality of values, and providing the sorted plurality of values as input to a second network layer of the neural network.

Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.

Abstract: A method for training a deep neural network (DNN), comprises receiving and formatting speech data for the training, performing Hessian-free sequence training (HFST) on a first subset of a plurality of subsets of the speech data, and iteratively performing the HFST on successive subsets of the plurality of subsets of the speech data, wherein iteratively performing the HFST comprises reusing information from at least one previous iteration.

Abstract: Methods and apparatus for using visual information to facilitate a speech recognition process. The method comprises dividing received audio information into a plurality of audio frames, determining for each of the plurality of audio frames, whether the audio information in the audio frame comprises speech from the foreground speaker, wherein the determining is based, at least in part, on received visual information, and transmitting the audio frame to an automatic speech recognition (ASR) engine for speech recognition when it is determined that the audio frame comprises speech from the foreground speaker.