Y.e. Hub Armenia LLC

Yandex Europe Ag

Vladimir Vladimirovich Kirichenko

Dmitry Mikhailovich Chernenkov

Aleksandr Aleksandrovich Molchanov

Artem Valerevich Babenko

Vladimir Andreevich Aliev

Daria Petrenko

Dmitry Aleksandrovich Baranchuk

Petr Vladislavovich Luferenko

Artem Panasyuk

A method and server for generating modified audio data for a video file are disclosed. The method includes acquiring a sequence of first audio portions, and a sequence of second audio portions in different languages. The method includes generating a plurality of candidate arrangements of the sequence of the second audio portions, where a given candidate arrangement is associated with candidate timestamps in the video file and candidate compression rates for respective ones from the sequence of second audio portions. The method includes selecting a target arrangement for the sequence of the second audio portions from the plurality of candidates. The selection is based on the target arrangement having a minimal penalty score amongst penalty scores associated with the plurality of candidates. The method includes generating at least one modified audio portion for the video file as a translation of the audio data using the target arrangement.

Method and a server for generating modified audio for a video

There is provided servers and methods of generating a waveform based on a spectrogram and a noise input. The method includes acquiring a trained flow-based vocoder including invertible blocks, and an untrained feed-forward vocoder including non-invertible blocks, which form a student-teacher network. The method includes executing a training process in the student-teacher network during which the server generates (i) a teacher waveform by the trained flow-based vocoder using a first spectrogram and a first noise input, (ii) a student waveform by the untrained feed-forward vocoder using the first spectrogram and the first noise input, and (iii) a loss value for the given training iteration using the teacher waveform and the student waveform. The server then trains the untrained feed-forward vocoder to generate the waveform. The trained feed-forward vocoder in then used lieu of the trained flow-based vocoder for generating waveforms based on spectrograms and noise inputs.

Method and a server for generating a waveform

There is disclosed a method of generating a text-to-speech (TTS) training set for training a Machine Learning Algorithm (MLA) for generating machine-spoken utterances The method is executable by a server. The method includes generating a synthetic word based on merging separate phonemes from each of two words of a corpus of pre-recorded utterances, the merging being done using the common phoneme as a merging anchor, the merging resulting in at least two synthetic words. The synthetic words and assessor labels are used to train a classifier to predict a quality parameter associated with a new synthetic phonemes-based word, the quality parameter being representative of whether the new synthetic phonemes-based word is naturally sounding (based on acoustic features of generated synthetic words utterances). The classifier is then used to generate training objects for the MLA and to use the MLA to process the corpus of pre-recorded utterances into their respective vectors.

Method and system for text-to-speech synthesis

Growing community of inventors

Moscow, Russia

Vladimir Vladimirovich Kirichenko