Abstract: Devices, systems, methods, media, and programs for detecting an emotional state change in an audio signal are provided. A number of segments of the audio signal are analyzed based on separate lexical and acoustic evaluations, and, for each segment, an emotional state and a confidence score of the emotional state are determined. A current emotional state of the audio signal is tracked for each of the number of segments. For a particular segment, it is determined whether the current emotional state of the audio signal changes to another emotional state based on the emotional state and a comparison of the confidence score of the particular segment to a predetermined threshold.

Abstract: A system and method for processing speech includes receiving a first information stream associated with speech, the first information stream comprising micro-modulation features and receiving a second information stream associated with the speech, the second information stream comprising features. The method includes combining, via a non-linear multilayer perceptron, the first information stream and the second information stream to yield a third information stream. The system performs automatic speech recognition on the third information stream. The third information stream can also be used for training HMMs.

Abstract: Devices, systems, methods, media, and programs for detecting an emotional state change in an audio signal are provided. A plurality of segments of the audio signal is received, with the plurality of segments being sequential. Each segment of the plurality of segments is analyzed, and, for each segment, an emotional state and a confidence score of the emotional state are determined. The emotional state and the confidence score of each segment are sequentially analyzed, and a current emotional state of the audio signal is tracked throughout each of the plurality of segments. For each segment, it is determined whether the current emotional state of the audio signal changes to another emotional state based on the emotional state and the confidence score of the segment.

Abstract: A pre-distortion system for improved mobile device communications via cancellation of nonlinear distortion is disclosed. The pre-distortion system may transmit an acoustic signal from a network to a device, wherein the acoustic signal includes a linear signal and a nonlinear cancellation signal that cancels at least a portion of nonlinear distortions created once a loudspeaker in the device emits the linear signal. Thus, when a loudspeaker of a mobile device is operating and nonlinear distortions are generated by the loudspeaker or adjacent components of the mobile device in close proximity to the loudspeaker, the pre-distortion system may create one or more nonlinear cancellation signals in the network. The nonlinear cancellation signal may be combined with the linear signal sent to the loudspeaker to cancel the nonlinear distortion signal created by the loudspeaker emitting acoustic sounds from the linear signal. Thus, the nonlinear cancellation signal becomes a pre-distortion signal.

Abstract: A system and method for processing speech includes receiving a first information stream associated with speech, the first information stream comprising micro-modulation features and receiving a second information stream associated with the speech, the second information stream comprising features. The method includes combining, via a non-linear multilayer perceptron, the first information stream and the second information stream to yield a third information stream. The system performs automatic speech recognition on the third information stream. The third information stream can also be used for training HMMs.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations.

Abstract: A system for exploiting visual information for enhancing audio signals via source separation and beamforming is disclosed. The system may obtain visual content associated with an environment of a user, and may extract, from the visual content, metadata associated with the environment. The system may determine a location of the user based on the extracted metadata. Additionally, the system may load, based on the location, an audio profile corresponding to the location of the user. The system may also load a user profile of the user that includes audio data associated with the user. Furthermore, the system may cancel, based on the audio profile and user profile, noise from the environment of the user. Moreover, the system may include adjusting, based on the audio profile and user profile, an audio signal generated by the user so as to enhance the audio signal during a communications session of the user.

Abstract: A system for sensor enhanced speech recognition is disclosed. The system may obtain visual content or other content associated with a user and an environment of the user. Additionally, the system may obtain, from the visual content, metadata associated with the user and the environment of the user. The system may also include determining, based on the visual content and metadata, if the user is speaking. If the user is determined to be speaking, the system may obtain audio content associated with the user and the environment. The system may then adapt, based on the visual content, audio content, and metadata, one or more acoustic models that match the user and the environment. Once the one or more acoustic models are adapted and loaded, the system may enhance a speech recognition process or other process associated with the user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations.

Abstract: Television content is provided upon request. A search request for television content is received from a user on a user device. Listings for television content that meet the search request are determined based on the search request. Text describing the listings is converted to corresponding speech describing the listings. Speech describing the listings is provided audibly.

Abstract: Devices, systems, methods, media, and programs for detecting an emotional state change in an audio signal are provided. A plurality of segments of the audio signal is received, with the plurality of segments being sequential. Each segment of the plurality of segments is analyzed, and, for each segment, an emotional state and a confidence score of the emotional state are determined. The emotional state and the confidence score of each segment are sequentially analyzed, and a current emotional state of the audio signal is tracked throughout each of the plurality of segments. For each segment, it is determined whether the current emotional state of the audio signal changes to another emotional state based on the emotional state and the confidence score of the segment.

Abstract: Devices, systems, methods, media, and programs for detecting an emotional state change in an audio signal are provided. A plurality of segments of the audio signal is received, with the plurality of segments being sequential. Each segment of the plurality of segments is analyzed, and, for each segment, an emotional state and a confidence score of the emotional state are determined. The emotional state and the confidence score of each segment are sequentially analyzed, and a current emotional state of the audio signal is tracked throughout each of the plurality of segments. For each segment, it is determined whether the current emotional state of the audio signal changes to another emotional state based on the emotional state and the confidence score of the segment.

Abstract: Disclosed herein are systems, methods, and computer-readable storage devices for processing audio signals. An example system configured to practice the method receives audio at a device to be transmitted to a remote speech processing system. The system analyzes one of noise conditions, need for an enhanced speech quality, and network load to yield an analysis. Based on the analysis, the system determines to bypass user-defined options for enhancing audio for speech processing. Then, based on the analysis, the system can modify an audio transmission parameter used to transmit the audio from the device to the remote speech processing system. The audio transmission parameter can be one of an amount of coding, a chosen codec, an amount of coding, or a number of audio channels, for example.

Abstract: A system and method for processing speech includes receiving a first information stream associated with speech, the first information stream comprising micro-modulation features and receiving a second information stream associated with the speech, the second information stream comprising features. The method includes combining, via a non-linear multilayer perceptron, the first information stream and the second information stream to yield a third information stream. The system performs automatic speech recognition on the third information stream. The third information stream can also be used for training HMMs.

Abstract: A network of intelligent electronic public signs interacts with one or many devices. A central server manages the electronic public signs and determines which one of the electronic public signs should display content related to a device. The central server may thus pair devices to electronic public signs for public display of individual content requests. Should any interaction involve personal or private information, the central server may exclude the corresponding response from public display. Any personal or private interactions may, instead, be privately conducted to prevent public display.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations.

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for detecting voice activity in a media signal in an augmented, multi-tier classifier architecture. A system configured to practice the method can receive, from a first classifier, a first voice activity indicator detected in a first modality for a human subject. Then, the system can receive, from a second classifier, a second voice activity indicator detected in a second modality for the human subject, wherein the first voice activity indicator and the second voice activity indicators are based on the human subject at a same time, and wherein the first modality and the second modality are different. The system can concatenate, via a third classifier, the first voice activity indicator and the second voice activity indicator with original features of the human subject, to yield a classifier output, and determine voice activity based on the classifier output.

Abstract: Concepts and technologies are disclosed herein for providing navigation routes and/or providing navigation route updates. According to various embodiments of the concepts and technologies disclosed herein, a navigation application can be configured to obtain route data from a routing service. The routing service can be configured to use navigation data locally stored and/or obtained from a number of sources to generate navigation routes and/or to update navigation routes. The generated and/or updated navigation routes can be provided to the user device as route data that can be used to provide navigation directions to a user.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for combining frame and segment level processing, via temporal pooling, for phonetic classification. A frame processor unit receives an input and extracts the time-dependent features from the input. A plurality of pooling interface units generates a plurality of feature vectors based on pooling the time-dependent features and selecting a plurality of time-dependent features according to a plurality of selection strategies. Next, a plurality of segmental classification units generates scores for the feature vectors. Each segmental classification unit (SCU) can be dedicated to a specific pooling interface unit (PIU) to form a PIU-SCU combination. Multiple PIU-SCU combinations can be further combined to form an ensemble of combinations, and the ensemble can be diversified by varying the pooling operations used by the PIU-SCU combinations.

Abstract: Concepts and technologies are disclosed herein for providing navigation routes and/or providing navigation route updates. According to various embodiments of the concepts and technologies disclosed herein, a navigation application can be configured to obtain route data from a routing service. The routing service can be configured to use navigation data locally stored and/or obtained from a number of sources to generate navigation routes and/or to update navigation routes. The generated and/or updated navigation routes can be provided to the user device as route data that can be used to provide navigation directions to a user.