Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 5. Отображено 5.
06-06-2023 дата публикации

Audio production method and device, terminal, storage medium and program product

Номер: CN116229996A
Автор: LIU ZHOU, CHEN LINLIN, PENG XUEJIE, MA ZHIWEI, CHEN CHUANYI
Принадлежит:

The embodiment of the invention provides an audio production method and device, a terminal, a storage medium and a program product, and relates to the technical field of application development. The method comprises the following steps: displaying identification information of a first audio file to be made; receiving a timbre making instruction sent by a user for the first audio file; adjusting the timbre of the first audio file based on the timbre making instruction, and generating a second audio file; wherein the second audio file is synthesized based on the singing feature of the first audio file and the timbre feature of the user. By adopting the technical scheme provided by the embodiment of the invention, the richness of the audio content can be improved.

Подробнее
Номер записи: 1
09-05-2023 дата публикации

Audio processing method and device, terminal, storage medium and program product

Номер: CN116092508A
Автор: SUN HONGWEN, CHEN CHUANYI, LAO ZHENFENG, GUAN DILING
Принадлежит:

The embodiment of the invention provides an audio processing method and device, a terminal, a storage medium and a program product, and relates to the technical field of audio. The method comprises the following steps: obtaining a singing feature of a first user extracted from a first audio file of a target song sung by the first user, wherein the singing feature of the first user is used for representing a singing style when the first user sings the target song; generating a second audio file according to the singing feature of the first user and the voiceprint feature of the second user; wherein the voiceprint feature of the second user is used for representing the tone of the second user. By adopting the technical scheme provided by the embodiment of the invention, the user tone in the audio file is modified into the tone of the other user, and the user listens to a song sung by the other user according to the singing style of the user, so that the second audio file has the characteristics ...

Подробнее
Номер записи: 2
11-08-2023 дата публикации

Tone conversion model training method, tone conversion method, device and equipment

Номер: CN116580693A
Автор: HUANG JIEXIONG, GUAN DILING, XUAN XIAOGUANG, OH DONG-HAE, CHEN CHUANYI
Принадлежит:

The invention discloses a tone conversion model training method, a tone conversion method, a device and equipment, and relates to the technical field of audio processing. The method comprises the following steps: acquiring audio content information, audio feature information and voiceprint features of a sample audio; inputting the audio content information, the audio feature information and the voiceprint features into a timbre conversion model, and outputting predicted acoustic features by the timbre conversion model; and according to the difference between the predicted acoustic features and the acoustic features of the sample audio, adjusting parameters of the tone conversion model to obtain a trained tone conversion model. The tone conversion model is trained by using the multiple audio features, so that the audio converted by the model has higher similarity with the target tone, and the pronunciation quality is better. Moreover, the training process for the timbre conversion model ...

Подробнее
Номер записи: 3
28-04-2023 дата публикации

Human voice symbol recognition model training method, human voice symbol recognition method and device

Номер: CN116034425A
Автор: LUO CHENGFANG, WAN JINGXUAN, CHEN CHUANYI
Принадлежит:

The invention discloses a training method of a human voice symbol recognition model, and a human voice symbol recognition method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring at least one annotated human voice audio, a human voice symbol annotation result corresponding to each annotated human voice audio, at least one pure human voice audio and at least one accompaniment audio; training the first network based on the annotated human voice audio, the accompaniment audio and a human voice symbol annotation result corresponding to the annotated human voice audio to obtain a trained first network; and training the second network based on the trained first network, the pure human voice audio and the accompaniment audio to obtain a human voice symbol recognition model. According to the obtained human voice symbol recognition model, a human voice accompaniment separation algorithm does not need to be called, and the ...

Подробнее
Номер записи: 4
28-04-2023 дата публикации

Audio processing method and device, equipment, storage medium and program product

Номер: CN116034423A
Автор: SUN HONGWEN, CHEN CHUANYI, OH DONG-HAE, LAO ZHENFENG, GUAN DILING
Принадлежит:

The embodiment of the invention provides an audio processing method and device, equipment, a storage medium and a program product, and relates to the technical field of audio. The method comprises: acquiring a first audio file (110); extracting an audio feature of the first audio file (120); processing the audio features through an acoustic model of the first user to generate a second audio file; wherein the acoustic model of the first user is a model in which acoustic features of the first user are learned, and the second audio file has a tone of the first user (130). By adopting the technical scheme provided by the embodiment of the invention, the richness of the audio content can be improved.

Подробнее
Номер записи: 5