Abstract: A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.

Abstract: A network device initiating WPS with a client device based on receiving a signal from a phone. The network device receives a feature number code from a phone connected to the network device. The feature number code is entered on the phone using a keypad and causes the network device to initiate WPS with a client device. The network device sends the phone a first signal indicating that WPS has been triggered. The network device determines a success of the WPS to connect the client device to the Wi-Fi network. The network device sends the phone a second signal indicating that the client device successfully connected to the Wi-Fi network. The first and second signals may be audio signals that are emitted by the speaker of the phone. The network device stores client device connection information in memory.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating waveforms conditioned on phoneme sequences. In one aspect, a method comprises: obtaining a phoneme sequence; processing the phoneme sequence using an encoder neural network to generate a hidden representation of the phoneme sequence; generating, from the hidden representation, a conditioning input; initializing a current waveform output; and generating a final waveform output that defines an utterance of the phoneme sequence by a speaker by updating the current waveform output at each of a plurality of iterations, wherein each iteration corresponds to a respective noise level, and wherein the updating comprises, at each iteration: processing (i) the current waveform output and (ii) the conditioning input using a noise estimation neural network to generate a noise output; and updating the current waveform output using the noise output and the noise level for the iteration.

Abstract: The present application provides a preparation method of a hydrogenated composite film and an optical filter, and relates to the field of optical film filter technologies. The preparation method includes: introducing inert gas and hydrogen into a reaction chamber, and bombarding at least two materials in the reaction chamber and the introduced hydrogen using plasma formed by the inert gas, such that the at least two materials are sputtered onto a substrate and react with hydrogen ions generated by the hydrogen to form a hydrogenated composite film layer. The hydrogenated composite film layer includes at least two materials which are co-sputtered onto the same substrate using the sputtering technology to obtain a required material performance, so as to obtain the hydrogenated composite film layer with a refractive index greater than 3.5 and an extinction coefficient less than 0.005 under a wavelength of 700 nm to 1800 nm.

Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.

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 distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.

Abstract: Onboarding one or more wireless devices to different wireless networks in a wireless system. A gateway/access point apparatus selects from a user interface a trigger service set identifier (SSID) among a plurality of available onboarding trigger SSIDs, each onboarding trigger SSID corresponding to a different wireless network. The gateway/access point apparatus transmits the onboarding trigger SSID to a wireless device, initiates an onboarding procedure between the wireless device and the gateway/access point apparatus, and establish a network connection between the wireless device and a wireless network based on the onboarding procedure, the wireless network corresponding to the transmitted onboarding trigger SSID. The selecting, the transmitting, the initiating, and the establishing are performed for each of the one or more wireless devices for establishing a network connection to a different one of the one or more wireless networks using a corresponding onboarding trigger SSID.

Abstract: In one embodiment, a method for remote management of a consumer premises equipment (CPE) via a network by use of an equipment management system includes an equipment management system including a processor and rendering on a display a field that accepts an input for a query by an operator. The equipment management system maintaining an associated database of characteristics of the plurality of consumer premises equipment including a serial number, a model, and a firmware. The equipment management system searching the database based upon the input from the query from the operator that includes the serial number, the model, and the firmware. The equipment management system in response to determining a match based upon the query rending information regarding a matching consumer premises equipment on the display.

Abstract: The present disclosure provides systems and methods for digital imaging and communications in medicine (DICOM) file processing. The methods may include receiving a request for processing a DICOM file. The DICOM file may include data of metadata and pixel data. The methods may also include parsing at least part of the metadata of the DICOM file. The methods may further include writing the data of the DICOM file to one or more data streams based on the parsed metadata.

Abstract: A method includes receiving an input text sequence to be synthesized into speech in a first language and obtaining a speaker embedding, the speaker embedding specifying specific voice characteristics of a target speaker for synthesizing the input text sequence into speech that clones a voice of the target speaker. The target speaker includes a native speaker of a second language different than the first language. The method also includes generating, using a text-to-speech (TTS) model, an output audio feature representation of the input text by processing the input text sequence and the speaker embedding. The output audio feature representation includes the voice characteristics of the target speaker specified by the speaker embedding.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators.

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: 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: Provided are a fingerprint identification device, a fingerprint identification method and an electronic device, which could improve security of fingerprint identification. The fingerprint identification device includes an optical fingerprint sensor including a plurality of pixel units; at least two filter units disposed above at least two of the plurality of pixel units, where each filter unit corresponds to one pixel unit, and the at least two filter units comprise filter units in at least two colors.

Abstract: A method of generating diverse and natural text-to-speech (TTS) samples includes receiving a text and generating a speech sample based on the text using a TTS model. A training process trains the TTS model to generate the speech sample by receiving training samples. Each training sample includes a spectrogram and a training text corresponding to the spectrogram. For each training sample, the training process identifies speech units associated with the training text. For each speech unit, the training process generates a speech embedding, aligns the speech embedding with a portion of the spectrogram, extracts a latent feature from the aligned portion of the spectrogram, and assigns a quantized embedding to the latent feature. The training process generates the speech sample by decoding a concatenation of the speech embeddings and a quantized embeddings for the speech units associated with the training text corresponding to the spectrogram.

Abstract: A network device for providing a LAN GUI to a client device. The network device receives a request for access by the client device to the LAN GUI. The network device analyzes a LAN GUI access whitelist and determines whether the client device is in the LAN GUI access whitelist. The client device is granted access to the LAN GUI without receiving a password from the client device when the client device is determined to be in the LAN GUI access whitelist. An address entry page may be presented to add the MAC address of the client device to the LAN GUI access whitelist and a password page may be presented to display the LAN GUI password. When the client device is not in the LAN GUI access list, a login page is presented for entering the password to obtain access to the LAN GUI.

Abstract: A method of transcribing speech using a multilingual end-to-end (E2E) speech recognition model includes receiving audio data for an utterance spoken in a particular native language, obtaining a language vector identifying the particular language, and processing, using the multilingual E2E speech recognition model, the language vector and acoustic features derived from the audio data to generate a transcription for the utterance. The multilingual E2E speech recognition model includes a plurality of language-specific adaptor modules that include one or more adaptor modules specific to the particular native language and one or more other adaptor modules specific to at least one other native language different than the particular native language. The method also includes providing the transcription for output.

Abstract: A method includes receiving a text input including a sequence of words represented as an input encoder embedding. The input encoder embedding includes a plurality of tokens, with the plurality of tokens including a first set of grapheme tokens representing the text input as respective graphemes and a second set of phoneme tokens representing the text input as respective phonemes. The method also includes, for each respective phoneme token of the second set of phoneme tokens: identifying a respective word of the sequence of words corresponding to the respective phoneme token and determining a respective grapheme token representing the respective word of the sequence of words corresponding to the respective phoneme token. The method also includes generating an output encoder embedding based on a relationship between each respective phoneme token and the corresponding grapheme token determined to represent a same respective word as the respective phoneme token.