Singing scoring method based on lyric and voice alignment

Abstract

The invention discloses a singing scoring method based on lyric and voice alignment. The singing scoring method comprises the following steps in sequence: song recording; voice accompaniment separation and noise removal; extraction of fundamental tone frequency and amplitude; alignment of lyrics with voice by taking sentences as units; segmentation of the fundamental tone frequency of each character in the aligned voice; calculation of a fundamental tone frequency similarity score; calculation of a rhythm score according to the duration of each sentence of user voice and standard voice and thestarting and ending time of each character; normalization of the amplitudes of the user voice and the standard voice; calculation of an amplitude similarity score; multiplying of the fundamental tonefrequency score, the rhythm score and the amplitude score by a weight coefficient and adding, and calculation of a comprehensive score of a song. According to the singing scoring method in the invention, the influence of accompaniment and noise on voice evaluation is reduced; label information of the lyrics is reasonably utilized, so that evaluation of the fundamental tone frequency and rhythm ofthe user is more accurate; and user songs are evaluated in multiple aspects, so that song scoring results are more objective and comprehensive.

Description

technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a singing scoring method based on alignment of lyrics and singing voices. Background technique [0002] With the development of the Internet and technology, modern people's offline and online singing entertainment needs are increasing, and users are paying more and more attention to the ranking of singing ability. Therefore, it is very necessary to propose an accurate and comprehensive singing scoring method . At present, the singing scoring method in the industry directly translates the recorded audio of the current sentence to be rated by n offset durations, so as to search for a better corresponding relationship between the recorded audio and the standard audio in time, and then improve the song's quality. sing score. However, this method needs to search n times each time to compare an optimal score, and the accuracy is not high enough. Therefore, some rese...

AI Technical Summary

Problems solved by technology

Although the academic circles have conducted in-depth research on singing scoring technology, these methods require a large amount of data and training time, and although there has been some research on song emotion analysis, the recognition accuracy is low, and the recognized emotional categories are relatively low. Single, difficult to achieve in practical applications

[0003] Although the singing scoring technology has developed to a certain extent in the past ten years, most of the methods in the academic circle are relatively complicated, have certain limitations, and are difficult to be directly applied to real life; therefore, relatively simple scoring methods are still used in the industry , resulting in insufficient ability to score songs

Images