Abstract: A target voice dataset may be augmented using speech prediction. Encoder and decoder models may be trained to encode audio data into encoded speech data, and convert it back to audio. The encoded units may include semantic information (e.g., phonemes and/or words) as well as feature data indicating prosody, timbre, speaker identity, speech style, emotion, etc. of speech. An acoustic/semantic language model (ASLM) may be configured to predict encoded speech data in a manner analogous to a language model predicting words; for example, based on preceding encoded speech data. The models may be used to generate synthesized speech samples having voice characteristics (e.g., feature data) similar to those of the target voice dataset. The augmented dataset may be used to train a text-to-speech (TTS) model to reproduce the target voice characteristics, and may improve performance of the TTS model over training with only the original target voice dataset.

Abstract: A text-to-speech (TTS) system may be configured to imitate characteristics of a target voice based on a limited dataset. The TTS system may include a machine learning model pre-trained using a synthetic parallel dataset and fine-tuned using examples of the target voice. A TTS component trained using a large single-speaker dataset may be used to generate the synthetic parallel dataset based on a multi-speaker dataset. The synthetic parallel dataset may include target audio data representing speech in the multi-speaker dataset and predicted audio data generated by the TTS component based on transcripts of the speech. The machine learning model may be pre-trained using the synthetic parallel dataset and fine-tuned using audio data representing target voice speech and predicted audio generated by the TTS component based on transcripts of the target voice speech. The trained model may be used to modify synthetic speech to approximate the characteristics of the target speech.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.

Abstract: A text-to-speech (TTS) system may be configured to imitate characteristics of a target voice based on a limited dataset. The TTS system may include a machine learning model pre-trained using a synthetic parallel dataset and fine-tuned using examples of the target voice. A TTS component trained using a large single-speaker dataset may be used to generate the synthetic parallel dataset based on a multi-speaker dataset. The synthetic parallel dataset may include target audio data representing speech in the multi-speaker dataset and predicted audio data generated by the TTS component based on transcripts of the speech. The machine learning model may be pre-trained using the synthetic parallel dataset and fine-tuned using audio data representing target voice speech and predicted audio generated by the TTS component based on transcripts of the target voice speech. The trained model may be used to modify synthetic speech to approximate the characteristics of the target speech.

Abstract: Apparatus and methods for extraction and calculation of multi-person performance metrics in a three-dimensional space. An example apparatus includes a detector to identify a first subject in a first image captured by a first image capture device based on a first set of two-dimensional kinematic keypoints in the first image, the two-dimensional kinematic keypoints corresponding to a joint of the first subject, the first image capture device associated with a first view of the first subject, a multi-view associator to verify the first subject using the first image and a second image captured by a second image capture device, the second image capture device associated with a second view of the first subject, the second view different than the first view, and a keypoint generator to generate three-dimensional keypoints for the first subject using the first set of two-dimensional kinematic keypoints.

Abstract: Predictive maintenance methods and systems, including a method of applying transfer entropy techniques to find a causal link between parameters; a method of applying quality weighting to context data based on a priori knowledge of the accuracy of the context data; a method of detecting a maintenance action from parameter data by detecting a step and a process capability improvement; a method of managing unattended alerts by considering cost/benefit of attending to one or more alerts over time and assigning alert expiry time and/or ranking the alerts accordingly; a method of displaying components of a complex system in a functional way enabling improvements in system diagnostics; a method of determining the time of an event indicator in time series parameter data; a method of classifying an event associated with a fault condition occurring within a system; and a method of determining whether an event recorded in parameter data is attributable to an external factor.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.

Abstract: Apparatus and methods for extraction and calculation of multi-person performance metrics in a three-dimensional space. An example apparatus includes a detector to identify a first subject in a first image captured by a first image capture device based on a first set of two-dimensional kinematic keypoints in the first image, the two-dimensional kinematic keypoints corresponding to a joint of the first subject, the first image capture device associated with a first view of the first subject, a multi-view associator to verify the first subject using the first image and a second image captured by a second image capture device, the second image capture device associated with a second view of the first subject, the second view different than the first view, and a keypoint generator to generate three-dimensional keypoints for the first subject using the first set of two-dimensional kinematic keypoints.

Abstract: A system is disclosed that includes a processor including watermark logic to output a first watermark to an output device that outputs a first watermark signal, based on the first watermark, to an acoustic transmission medium. The processor also includes recording logic to capture, at a first time period, an authentication submission comprising the first watermark signal convolved, via the acoustic transmission medium, with a first passphrase signal. The system also includes a dynamic random access memory (DRAM). Other embodiments are disclosed and claimed.

Abstract: Cepstral variance normalization is described for audio feature extraction.

Abstract: A system is disclosed that includes a processor including watermark logic to output a first watermark to an output device that outputs a first watermark signal, based on the first watermark, to an acoustic transmission medium. The processor also includes recording logic to capture, at a first time period, an authentication submission comprising the first watermark signal convolved, via the acoustic transmission medium, with a first passphrase signal. The system also includes a dynamic random access memory (DRAM). Other embodiments are disclosed and claimed.

Abstract: A system is disclosed that includes a processor including watermark logic to output a first watermark to an output device that outputs a first watermark signal, based on the first watermark, to an acoustic transmission medium. The processor also includes recording logic to capture, at a first time period, an authentication submission comprising the first watermark signal convolved, via the acoustic transmission medium, with a first passphrase signal. The system also includes a dynamic random access memory (DRAM). Other embodiments are disclosed and claimed.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.

Abstract: Cepstral variance normalization is described for audio feature extraction.

Abstract: Predictive maintenance methods and systems, including a method of applying transfer entropy techniques to find a causal link between parameters; a method of applying quality weighting to context data based on a priori knowledge of the accuracy of the context data; a method of detecting a maintenance action from parameter data by detecting a step and a process capability improvement; a method of managing unattended alerts by considering cost/benefit of attending to one or more alerts over time and assigning alert expiry time and/or ranking the alerts accordingly; a method of displaying components of a complex system in a functional way enabling improvements in system diagnostics; a method of determining the time of an event indicator in time series parameter data; a method of classifying an event associated with a fault condition occurring within a system; and a method of determining whether an event recorded in parameter data is attributable to an external factor.

Abstract: Various embodiments are generally directed to pairing computing devices for collaborative interaction via a network through a centralized secure device pairing service. An apparatus comprises a controller processor circuit, and a controller storage communicatively coupled to the controller processor circuit to store an initial private key and to store instructions that when executed by the controller processor circuit cause the controller processor circuit to create a first signature using the initial private key, transmit the first signature to an issuing server via a network, receive a group public key and an associated member private key from the issuing server, create a second signature using the member private key, transmit the second signature to a member device via the network; receive a third signature from the member device; and authenticate the third signature using the group public key. Other embodiments are described and claimed herein.

Abstract: Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include intermediate scoring of a state or states of a key phrase model and/or a backward transition or rejection loopback from a state of the key phrase model to a rejection model to reduce false accepts based on received utterances.

Abstract: Providing optical watermark signals for a visual authentication session by performing at least the following: receive, at an anti-spoof engine, an instruction to perform visual authentication operations for a visual authentication session, generate, with the anti-spoof engine, an optical watermark signal based on receiving the instruction, wherein the optical watermark signal includes at least one optical identifier to authenticate images captured during the visual authentication session, obtain, with the anti-spoof engine, an image source that includes captured images of the visual authentication session, determine, with the anti-spoof engine, whether the image source includes a reflected optical watermark signal, and compare, with the anti-spoof engine, whether the reflected optical watermark signal matches the generated optical watermark signal based on the determination that the image source includes the reflected optical watermark signal.