Abstract: In one embodiment, an AR/VR system includes a social-networking application installed on the AR/VR system, which allows a user to access on online social network, including communicating with the user's social connections and interacting with content objects on the online social network. The AR/VR system also includes an AR/VR application, which allows the user to interact with an AR/VR platform by providing user input to the AR/VR application via various modalities. Based on the user input, the AR/VR platform generates responses and sends the generated responses to the AR/VR application, which then presents the responses to the user at the AR/VR system via various modalities.

Abstract: The present disclosure provides an artificial intelligence (AI) system for sequence-to-sequence modeling with attention adapted for streaming applications. The AI system comprises at least one processor; and memory having instructions stored thereon that, when executed by the processor, cause the AI system to process each input frame in a sequence of input frames through layers of a deep neural network (DNN) to produce a sequence of outputs. At least some of the layers of the DNN include a dual self-attention module having a dual non-causal and causal architecture attending to non-causal frames and causal frames. Further, the AI system renders the sequence of outputs.

Abstract: An audio processing system is provided. The audio processing system comprises an input interface configured to accept an audio signal. Further, the audio processing system comprises a memory configured to store a neural network trained to determine different types of attributes of multiple concurrent audio events of different origins, wherein the types of attributes include time-dependent and time-agnostic attributes of speech and non-speech audio events. Further, the audio processing system comprises a processor configured to process the audio signal with the neural network to produce metadata of the audio signal, the metadata including one or multiple attributes of one or multiple audio events in the audio signal.

Abstract: The present disclosure provides an artificial intelligence (AI) system for sequence-to-sequence modeling with attention adapted for streaming applications. The AI system comprises at least one processor; and memory having instructions stored thereon that, when executed by the processor, cause the AI system to process each input frame in a sequence of input frames through layers of a deep neural network (DNN) to produce a sequence of outputs. At least some of the layers of the DNN include a dual self-attention module having a dual non-causal and causal architecture attending to non-causal frames and causal frames. Further, the AI system renders the sequence of outputs.

Abstract: An artificial intelligence (AI) system is disclosed. The AI system includes a processor that processes a sequence of input frames with a neural network including a dilated self-attention module trained to compute a sequence of outputs by transforming each input frame into a corresponding query frame, a corresponding key frame, and a corresponding value frame leading to a sequence of key frames, a sequence of value frames, and a sequence of query frames of same ordering and by performing attention calculations for each query frame with respect to a combination of a portion of the sequences of key and value frames restricted based on a location of the query frame and a dilation sequence of the key frames and a dilation sequence of value frames extracted by processing different frames of the sequences of key and value frames with a predetermined extraction function. Further, the processor renders the sequence of outputs.

Abstract: An artificial intelligence (AI) system is disclosed. The AI system includes a processor that processes a sequence of input frames with a neural network including a dilated self-attention module trained to compute a sequence of outputs by transforming each input frame into a corresponding query frame, a corresponding key frame, and a corresponding value frame leading to a sequence of key frames, a sequence of value frames, and a sequence of query frames of same ordering and by performing attention calculations for each query frame with respect to a combination of a portion of the sequences of key and value frames restricted based on a location of the query frame and a dilation sequence of the key frames and a dilation sequence of value frames extracted by processing different frames of the sequences of key and value frames with a predetermined extraction function. Further, the processor renders the sequence of outputs.

Abstract: A speech recognition system successively processes each encoder state of encoded acoustic features with a frame-synchronous decoder (FSD) and label-synchronous decoder (LSD) modules. Upon identifying an encoder state carrying information about new transcription output, the system expands a current list of FSD prefixes with FSD module, evaluates the FSD prefixes with LSD module, and prunes the FSD prefixes according to joint FSD and LSD scores. FSD and LSD modules are synchronized by having LSD module to process the portion of the encoder states including new transcription output identified by the FSD module and to produce LSD scores for the FSD prefixes determined by the FSD module.

Abstract: A method for training a neural network with a graph-based temporal classification (GTC) objective function, using a directed graph of nodes connected by edges representing labels and transitions among the labels, is provided. The directed graph specifies one or a combination of non-monotonic alignment between a sequence of labels and a sequence of probability distributions and constraints on the label repetitions. The method comprises executing a neural network to transform a sequence of observations into the sequence of probability distributions, and updating parameters of the neural network based on the GTC objective function configured to maximize a sum of conditional probabilities of all possible sequences of labels that are generated by unfolding the directed graph to the length of the sequence of observations and mapping each unfolded sequence of nodes and edges to a possible sequence of labels.

Abstract: This invention relates generally to speech processing and more particularly to end-to-end automatic speech recognition (ASR) that utilizes long contextual information. Some embodiments of the invention provide a system and a method for end-to-end ASR suitable for recognizing long audio recordings such as lecture and conversational speeches. This disclosure includes a Transformer-based ASR system that utilizes contextual information, wherein the Transformer accepts multiple utterances at the same time and predicts transcript for the last utterance. This is repeated in a sliding-window fashion with one-utterance shifts to recognize the entire recording. In addition, some embodiments of the present invention may use acoustic and/or text features obtained from only the previous utterances spoken by the same speaker as the last utterance when the long audio recording includes multiple speakers.

Abstract: An audio processing system is provided. The audio processing system comprises an input interface configured to accept an audio signal. Further, the audio processing system comprises a memory configured to store a neural network trained to determine different types of attributes of multiple concurrent audio events of different origins, wherein the types of attributes include time-dependent and time-agnostic attributes of speech and non-speech audio events. Further, the audio processing system comprises a processor configured to process the audio signal with the neural network to produce metadata of the audio signal, the metadata including one or multiple attributes of one or multiple audio events in the audio signal.

Abstract: A speech recognition system includes an encoder to convert an input acoustic signal into a sequence of encoder states, an alignment decoder to identify locations of encoder states in the sequence of encoder states that encode transcription outputs, a partition module to partition the sequence of encoder states into a set of partitions based on the locations of the identified encoder states, and an attention-based decoder to determine the transcription outputs for each partition of encoder states submitted to the attention-based decoder as an input. Upon receiving the acoustic signal, the system uses the encoder to produce the sequence of encoder states, partitions the sequence of encoder states into the set of partitions based on the locations of the encoder states identified by the alignment decoder, and submits the set of partitions sequentially into the attention-based decoder to produce a transcription output for each of the submitted partitions.

Abstract: A speech recognition system successively processes each encoder state of encoded acoustic features with a frame-synchronous decoder (FSD) and label-synchronous decoder (LSD) modules. Upon identifying an encoder state carrying information about new transcription output, the system expands a current list of FSD prefixes with FSD module, evaluates the FSD prefixes with LSD module, and prunes the FSD prefixes according to joint FSD and LSD scores. FSD and LSD modules are synchronized by having LSD module to process the portion of the encoder states including new transcription output identified by the FSD module and to produce LSD scores for the FSD prefixes determined by the FSD module.

Abstract: A speech recognition system includes an encoder to convert an input acoustic signal into a sequence of encoder states, an alignment decoder to identify locations of encoder states in the sequence of encoder states that encode transcription outputs, a partition module to partition the sequence of encoder states into a set of partitions based on the locations of the identified encoder states, and an attention-based decoder to determine the transcription outputs for each partition of encoder states submitted to the attention-based decoder as an input. Upon receiving the acoustic signal, the system uses the encoder to produce the sequence of encoder states, partitions the sequence of encoder states into the set of partitions based on the locations of the encoder states identified by the alignment decoder, and submits the set of partitions sequentially into the attention-based decoder to produce a transcription output for each of the submitted partitions.

Abstract: A method for at least partially treating biologically active sols, gels, mixtures or composites of sols and gels, and/or sol-gel derived materials, the sols, gels, mixtures or composites of sols and gels, and/or sol-gel derived materials having OH-groups and being at least partially amorphous, the treatment being performed with a localised electromagnetic and/or acoustic energy. A method for coating a device with biologically active sols, gels, mixtures or composites of sols and gels, and/or sol-gel derived materials and a method for modifying the biological activity of biologically active sols, gels, mixtures or composites of sols and gels, and/or sol-gel derived materials are also disclosed. Both methods include treatment with localised electromagnetic and/or acoustic energy. Also disclosed is the use of the method to fabricate different devices and to attach at least two devices.

Abstract: The object of the invention is to provide a method for sintering bioactive glass or bioactive glass composite. The method according to the invention is characterised in that the sintering is performed with a localised electromagnetic and/or acoustic energy. Other objects of the invention are a method for coating a device with bioactive glass or bioactive glass composite and a method for attaching at least two devices. All these methods use sintering with localised electromagnetic and/or acoustic energy.