Singing evaluation method and system

Abstract

The invention discloses a singing evaluation method and system and belongs to the technical field of voice signal processing. The singing evaluation method comprises the following steps: obtaining record data of a current sentence of a user singing song; obtaining standard musical score data of the current sentence; searching the optimum offset frame number within the search window length range at the start position of the record data comprising the current sentence; carrying out translation on the record data of the current sentence according to the optimum offset frame number to enable the record data of the current sentence to be synchronous with the standard musical score data in time; carrying out grading on the record data of the current sentence obtained after translation; and obtaining a score result of the user singing song according to the score of each sentence of the user singing song. The singing evaluation method is simple in calculation process and accurate to grade, and can meet real-time application requirement.

Description

Technical field [0001] The invention relates to the technical field of speech signal processing, in particular to a singing evaluation method and system. Background technique [0002] With the rapid development of mobile Internet technology, people can easily and quickly realize the demand for singing anytime and anywhere. More and more KTV or online singing software have begun to evaluate the singing level of users, thereby increasing the entertainment of singing. Due to the influence of K song equipment software or hardware and other factors, such as: (1) There is a time difference between the response time of the recording equipment and the playback time; (2) The quality of the recording hardware equipment is poor, and the stability of the recording sampling rate cannot be guaranteed; (3) ) The playing time of the song is difficult to obtain, and it may not be possible to accurately read the playback progress at each moment during the song playing process. For example, when re...

AI Technical Summary

Problems solved by technology

When using the original singing of a song with an accompaniment, since the standard original singing contains the sound of the accompaniment, it will interfere with the synchronization operation, and the accompaniment sound is also difficult to accurately eliminate; when using data recorded by music professionals, it will cause cost Direct improvement; and when DWT is used to realize synchronous operation, the calculation of the cost of each step is generally performed in units of frames, resulting in a large amount of calculation, which is difficult to meet the requirements of real-time scoring

Images