Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.

Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing data generated by a sensing system that rotationally senses an environment. In one aspect, a method comprises partitioning a predetermined period of time into a plurality of sub-periods, wherein the predetermined period of time is a period of time for which data generated by the sensing system constitutes a complete rotational sensing of the environment; for each sub-period: receiving current data generated by the sensing system during the sub-period and characterizing a respective partial scene of the environment; processing the current data using an object detection neural network to generate a current object detection output that is specific to the respective partial scene of the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural machine translation. One of the systems includes an encoder neural network comprising: an input forward long short-term memory (LSTM) layer configured to process each input token in the input sequence in a forward order to generate a respective forward representation of each input token, an input backward LSTM layer configured to process each input token in a backward order to generate a respective backward representation of each input token and a plurality of hidden LSTM layers configured to process a respective combined representation of each of the input tokens in the forward order to generate a respective encoded representation of each of the input tokens; and a decoder subsystem configured to receive the respective encoded representations and to process the encoded representations to generate an output sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses N-best lists of decoded hypotheses, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

Abstract: Described herein are methods and systems associated with viewing condition adaption of multimedia content. A method for receiving multimedia content with a device from a network may include determining a viewing parameter, transmitting a request for the multimedia content to the network, whereby the request may be based on the viewing parameter, and receiving the multimedia content from the network, whereby the multimedia content may be processed at a rate according to the viewing parameter. The viewing parameter may include at least one of: a user viewing parameter, a device viewing parameter, or a content viewing parameter. The method may further include receiving a multimedia presentation description (MPD) file from the network. The MPD file may include information relating to the rate of the multimedia content and information relating to the rate may include a descriptor relating to the viewing parameter, whereby the descriptor may be required or optional.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. The methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.

Abstract: The present disclosure provides systems and methods that train and use machine-learned models such as, for example, sequence-to-sequence models, to perform direct and text-free speech-to-speech translation. In particular, aspects of the present disclosure provide an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation.

Abstract: The present invention relates to monoclonal antibodies which have high anti-RSV neutralizing titers. The invention further provides for isolated nucleic acids encoding the antibodies of the invention and host cells transformed therewith. The invention yet further provides for diagnostic, prophylactic and therapeutic methods employing the antibodies and nucleic acids of the invention, particularly as a passive immunotherapy agent in infants and the elderly.

Abstract: The present invention relates to monoclonal antibodies which have high anti-RSV neutralizing titers. The invention further provides for isolated nucleic acids encoding the antibodies of the invention and host cells transformed therewith. The invention yet further provides for diagnostic, prophylactic and therapeutic methods employing the antibodies and nucleic acids of the invention, particularly as a passive immunotherapy agent in infants and the elderly.

Abstract: The present invention relates to a system for effectively identifying pressing line of vehicle and giving an early prompt, comprising an image acquisition module, a lane line extraction module, a distance calculation module and an early-warning judgment module. The image acquisition module acquires front images through an optical camera. The lane line extraction module processes the front images to extract lane lines in each of the images. The distance calculation module calculates a distance between the optical camera and each of left and right lane lines, and calculates the distance between the vehicle and each of the left and right lane lines through the position of the camera in the vehicle and vehicle dimensions. Then, the early-warning judgment module judges whether or not to give a driver an early-warning prompt.

Abstract: Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.

Abstract: Provided are a granulated blast-furnace slag activator and a method of manufacturing the same. The granulated blast-furnace slag activator includes, in percent by weight, the following raw materials: 62% to 95% of gypsum and 5% to 38% of high belite sulfoaluminate cement clinker. Also provided is a method of manufacturing cement by mixing the granulated blast-furnace slag activator with granulated blast-furnace slag at a certain ratio.

Abstract: A service processing method is applied to a system including a first distributed node and at least two second distributed nodes to ensure correct service processing. The first distributed node communicates with a controller using the second distributed nodes. The service processing method performed by the first distributed node, includes obtaining a first operation request, where the first operation request includes a first service object, allocating a first identification code to the first operation request according to a preset rule, where the first identification code identifies a processing sequence of the first operation request for the first service object, and sending the first operation request and the first identification code to the controller using a second distributed node such that the controller determines, according to the preset rule and the first identification code, whether the first operation request needs to be processed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training giant neural networks. One of the methods includes obtaining data specifying a partitioning of the neural network into N composite layers that form a sequence of composite layers, wherein each composite layer comprises a distinct plurality of layers from the multiple network layers of the neural network; obtaining data assigning each of the N composite layers to one or more computing devices from a set of N computing devices; partitioning a mini-batch of training examples into a plurality of micro-batches; and training the neural network, comprising: performing a forward pass through the neural network until output activations have been computed for each micro-batch for a final composite layer in the sequence, and performing a backward pass through the neural network until output gradients have been computed for each micro-batch for the first composite layer in the sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Abstract: A miter saw that includes a base, a worktable arranged on the base and defining a worktable plane, and a cutting head formed with or connected to an operating member operable by a user. The cutting head further includes a circular saw blade operative to rotate around a first axis and a motor operative to drive the circular saw blade. A fence is arranged on the worktable. The cutting head is further connected to a first guiding member configured for guiding chips to be discharged. The fence is formed with a guiding portion. The cutting head is operative to rotate around a second axis parallel to the worktable plane and, when the cutting head rotates around the second axis, the guiding portion is operative to guide the first guiding member to cross the fence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

Abstract: Quality-based optimizations of a delivery process of streaming content may be enabled. The optimization may take the form of quality-based switching. To enable quality-based switching in a streaming client, the client may have access to information about the quality of an encoded segment and/or sub-segment. Quality-related information may include any number of added quality metrics relating to an encoded segment and/or sub-segment of an encoded video stream. The addition of quality-related information may be accomplished by including the quality-related information in a manifest file, including the quality-related information in segment indices stored in a segment index file, and/or providing additional files with quality-related segment information and providing a link to the information from an MPD file. Upon receiving the quality-related information, the client may request and receive a stream that has a lower bitrate, thereby saving bandwidth while retaining quality of the streaming content.