Abstract: Systems and methods for machine learning based audio watermarking for videoconferencing are provided. For example, a computing device accesses an original audio signal and a watermark to be embedded into the original audio signal and extracts, using an audio encoder, a set of audio features from the original audio signal. The audio encoder is a machine learning model. The computing device further extracts, using a watermark encoder, a set of watermark features from the watermark. The watermark encoder is also a machine learning model. The computing device combines the set of audio features and the set of watermark features to generate a set of features, compresses the set of features, and transmits the compressed set of features.

Abstract: Provided are an audio synthesis method and apparatus, an electronic device, and a readable storage medium. In the present solution, conversion from a text to an audio having a target timbre is achieved by means of a pre-trained voice synthesis model, the voice synthesis model comprising a first feature extraction sub-model and a second feature extraction sub-model, wherein the first feature extraction sub-model outputs, according to an inputted text to be processed, an acoustic feature comprising a bottleneck feature; the second feature extraction sub-model outputs, according to the inputted first acoustic features, a Mel spectrum feature corresponding to the text to be processed; according to the Mel spectrum feature corresponding to the text to be processed, the target audio corresponding to the text to be processed is obtained, and the target audio has the target timbre.

Abstract: Techniques for cross-lingual voice cloning for low-resource languages are provided. In an example method, a computing device receives a first speech sample, the first speech sample characterized by a first voice and spoken in a first language and a text input in a second language. The computing device generates, using a first trained ML model trained to encode the text input to an encoded representation that characterizes the text input spoken in a second voice in the second language, the encoded representation of the text input. The computing device generates, using a second trained ML model trained to generate a spectrogram based on the encoded representation of the text input spoken in the second language, the spectrogram of the text input, the spectrogram characterized by the text input spoken in the first voice in the second language. The computing device generates an audio output based on the spectrogram.

Abstract: Systems and methods of multi-modal adversarial training for zero-shot voice cloning are provided. A communication platform provides training transcript data and training speaker data to a text-to-speech (TTS) model to obtains synthesized audio data comprising synthesized acoustic features and synthesized prosodic features. The communication platform determines determine a first classification prediction using a first discriminator model and a second classification prediction using a second discriminator model. The communication platform trains the first discriminator model and the second discriminator model based on the first classification prediction and the second classification prediction. The communication platform trains the TTS model to obtain a trained TTS model based on ground truth acoustic features, ground truth prosodic features, the synthesized acoustic features, the synthesized prosodic features, the first classification prediction, and the second classification prediction.

Abstract: An impeller includes a hub having an axial direction as a rotation axis and extending from a first end to a second end, and including an end surface and a first wall. The end surface is positioned at the first end of the hub, one end of the first wall extends around an entire periphery of the end surface and radially outwardly extends at an angle toward the second end in the axial direction. A length of extension of the first wall is greater than 50% of a length of extension of the hub. The impeller further includes a plurality of blades, the proximal ends of which extend from the periphery of the hub in a radial direction. A predetermined range of angle is formed between the first wall and the axial direction, and the predetermined range of angle is between 3 degrees and 45 degrees.

Abstract: An impeller includes a hub having an axial direction as a rotation axis and extending from a first end to a second end, and including an end surface and a first wall. The end surface is positioned at the first end of the hub, one end of the first wall extends around an entire periphery of the end surface and radially outwardly extends at an angle toward the second end in the axial direction. A length of extension of the first wall is greater than 50% of a length of extension of the hub. The impeller further includes a plurality of blades, the proximal ends of which extend from the periphery of the hub in a radial direction. A predetermined range of angle is formed between the first wall and the axial direction, and the predetermined range of angle is between 3 degrees and 45 degrees.

Abstract: Provided are an audio synthesis method and apparatus, an electronic device, and a readable storage medium. In the present solution, conversion from a text to an audio having a target timbre is achieved by means of a pre-trained voice synthesis model, the voice synthesis model comprising a first feature extraction sub-model and a second feature extraction sub-model, wherein the first feature extraction sub-model outputs, according to an inputted text to be processed, an acoustic feature comprising a bottleneck feature; the second feature extraction sub-model outputs, according to the inputted first acoustic features, a Mel spectrum feature corresponding to the text to be processed; according to the Mel spectrum feature corresponding to the text to be processed, the target audio corresponding to the text to be processed is obtained, and the target audio has the target timbre.