Audio retrieval method, device and equipment and storage medium

Abstract

The invention discloses an audio retrieval method, device and equipment and a storage medium, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring a first audio; determining the category of the first audio based on a pre-trained classification model, the category comprising a first category or a second category, the first category being used for indicating that the volume relationship between the noise audio in the first audio and the human voice audio satisfies a preset condition, the second category being used for indicating that the volume relationship between the noise audio and the human voice audio in the first audio does not meet the preset condition; if the category of the first audio is the first category, retrieving a second audio matched with the first audio; and if the category of the first audio is the second category, controlling to output retrieval failure prompt information. According to the invention, the process of retrieving the audio with relatively high noise and the process of playing and listening to the song audios in the retrieval result one by one by the user can be omitted, so that the time of the processes is saved.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a method, device, device and storage medium for retrieving audio. Background technique [0002] With the development of information technology and network technology, the scale of music library has increased exponentially, and the rapid retrieval of music songs has become a new research hotspot. Traditional music retrieval methods are mainly based on text keyword retrieval, and perform audio retrieval of related songs according to text information such as song title, singer, genre, and lyrics input by users. In order to facilitate users to search, a new music retrieval method has emerged as the times require. This method can retrieve the audio sung by the user, and then when the user cannot provide the exact song name, singer and other text information, in the The corresponding song audio is retrieved from the music library. [0003] In related technologies, ...

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present application provides a method, device, device, and storage medium for retrieving audio, which can solve the process of retrieving audio with high noise, and the user can play and listen to the retrieval results obtained based on the audio with high noise. The process of wasting the user's time

Images