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 invention provides an actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation. The method includes: preprocessing actually-measured marine environment data; calculating a target function value; calculating a gradient value of a target function; calculating a minimum value of the target function; extracting space multi-scale information from the actually-measured data; and updating background field data to form a final data assimilation analysis field. The present invention improves the traditional recursive filtering three-dimensional variation method, and sequentially assimilates information with different scales, thereby effectively overcoming the problem that multi-scale information cannot be effectively extracted by a traditional three-dimensional variation method.

Abstract: The present invention provides an actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation. The method includes: preprocessing actually-measured marine environment data; calculating a target function value; calculating a gradient value of a target function; calculating a minimum value of the target function; extracting space multi-scale information from the actually-measured data; and updating background field data to form a final data assimilation analysis field. The present invention improves the traditional recursive filtering three-dimensional variation method, and sequentially assimilates information with different scales, thereby effectively overcoming the problem that multi-scale information cannot be effectively extracted by a traditional three-dimensional variation method.