Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: A speaker recognition system includes a previously-trained joint neural network. An enrollment machine of the speaker recognition system is configured to operate the previously-trained joint neural network to enroll a new speaker based on audiovisual data featuring the newly enrolled speaker. A recognition machine of the speaker recognition system is configured to operate the previously-trained joint neural network to recognize a previously-enrolled speaker based on audiovisual data featuring the previously-enrolled speaker.

Abstract: Improvements in speaker identification and verification are provided via an attention model for speaker recognition and the end-to-end training thereof. A speaker discriminative convolutional neural network (CNN) is used to directly extract frame-level speaker features that are weighted and combined to form an utterance-level speaker recognition vector via the attention model. The CNN and attention model are join-optimized via an end-to-end training algorithm that imitates the speaker recognition process and uses the most-similar utterances from imposters for each speaker.

Abstract: Improvements in speaker identification and verification are provided via an attention model for speaker recognition and the end-to-end training thereof. A speaker discriminative convolutional neural network (CNN) is used to directly extract frame-level speaker features that are weighted and combined to form an utterance-level speaker recognition vector via the attention model. The CNN and attention model are join-optimized via an end-to-end training algorithm that imitates the speaker recognition process and uses the most-similar utterances from imposters for each speaker.

Abstract: The present invention is a photovoltaic-thermoelectric solar cell and a method of manufacturing a photovoltaic-thermoelectric solar cell. The solar cell includes a substantially transparent electrode, an organometallic photovoltaic material disposed on the transparent electrode, and a cathode disposed on the organometallic photovoltaic material. The organometallic photovoltaic material may be a porphyrin nanomaterial.

Abstract: Aspects of the technology described herein relate to a new type of deep neural network (DNN). The new DNN is described herein as a deep neural support vector machine (DNSVM). Traditional DNNs use the multinomial logistic regression (softmax activation) at the top layer and underlying layers for training. The new DNN instead uses a support vector machine (SVM) as one or more layers, including the top layer. The technology described herein can use one of two training algorithms to train the DNSVM to learn parameters of SVM and DNN in the maximum-margin criteria. The first training method is a frame-level training. In the frame-level training, the new model is shown to be related to the multi-class SVM with DNN features. The second training method is the sequence-level training. The sequence-level training is related to the structured SVM with DNN features and HMM state transition features.