CN-121983007-A - Song playing method and device, electronic equipment and storage medium

CN121983007ACN 121983007 ACN121983007 ACN 121983007ACN-121983007-A

Abstract

The application discloses a song playing method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of determining a target cut-out time point of a first song from candidate cut-out time points based on first difference information of audio characteristic information of the first song and second song, and determining a target cut-in time point of a second song from the candidate cut-in time points; and responding to the position corresponding to the target cut-out time point of the first song, and processing and playing the first music segment corresponding to the target cut-out time point of the first song and the second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameters. Therefore, the transition processing parameters for connecting two songs can be dynamically determined, and corresponding song connection processing is further executed, so that seamless connection effects of continuous rhythm and natural hearing are achieved.

Inventors

JIN QIANG
LIN YONGPING
MA JIANLI
LI PENG
LI YIHUI
LIU HUAPING
CHEN JINHAI

Assignees

杭州网易云音乐科技有限公司

Dates

Publication Date: 20260505
Application Date: 20251231

Claims (10)

1. A method of playing a song, the method comprising: Acquiring characteristic information of a first song and a second song, wherein the characteristic information comprises audio characteristic information and structural characteristic information, and the second song is a song played after the first song; Determining a candidate cut-out time point of the first song based on the structural feature information of the first song, and determining a candidate cut-in time point of the second song based on the structural feature information of the second song; determining a target cut-out time point of the first song from the candidate cut-out time points based on first difference information of audio feature information of the first song and the second song, and determining a target cut-in time point of the second song from the candidate cut-in time points; Determining transition processing parameters of a first music segment corresponding to a target cut-out time point of the first song and a second music segment corresponding to a target cut-in time point of the second song based on the audio characteristic information of the first song and the second song; and responding to the first song to be played to the position corresponding to the target cut-out time point, and processing and playing a first music segment corresponding to the target cut-out time point of the first song and a second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameters.
2. The song playing method of claim 1, wherein the determining the candidate cut-out time point of the first song based on the structural feature information of the first song, and the determining the candidate cut-in time point of the second song based on the structural feature information of the second song comprises: Searching a first key time point under each preset key time point type in a first song based on the structural feature information of the first song and a plurality of preset key time point types, and taking the first key time point as a candidate cutting time point; searching a second key time point under each preset key time point type in the second song based on the structural feature information of the second song and a plurality of preset key time point types, and taking the second key time point as a candidate cut-in time point.
3. The song playing method according to claim 2, wherein the structural feature information includes at least one of a singing start-stop time point, a performance start-stop time point of a designated musical instrument, and musical piece structural information including a type of at least one musical piece and start-stop time information of each of the musical pieces; The preset key time point type comprises singing key time points, a designated musical instrument playing key time point, a designated structural key time point and a designated section key time point; the key time point of the singing voice is determined based on the start and stop time point of the singing voice; the performance key time points of the specified musical instrument are determined based on the performance start-stop time points; The key time point of the structure is determined based on the start-stop time information of the appointed music paragraph; The bar key time point is determined based on a preset re-beat time point.
4. The song playing method according to claim 3, wherein the type combination of the types of the preset key time points of the candidate cut-out time point and the candidate cut-in time point is provided with corresponding priorities, and the order of the priorities from high to low is that the types of the key time points of playing, the key time points of structure, the key time points of singing and the key time points of sections are combined, and other types of the types are combined; The determining a target cut-out time point of the first song from the candidate cut-out time point based on first difference information of audio feature information of the first song and the second song, and determining a target cut-in time point of the second song from the candidate cut-in time point, includes: Determining at least one type combination formed by the candidate cutting-out time point and the candidate cutting-in time point based on the preset key time point type of the candidate cutting-out time point and the preset key time point type of the candidate cutting-in time point; determining a target cut-out time point of the first song and determining a target cut-in time point of the second song based on a highest priority type combination and first difference information of audio feature information of the first song and the second song.
5. The song playing method according to any one of claims 1-4, wherein the transition processing parameters include transition time and song processing parameters, The processing and playing the first music segment corresponding to the target cut-out time point of the first song and the second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameter in response to the first song being played to the position corresponding to the target cut-out time point, includes: taking a music piece of the transition time at which the target cut-in time point is positioned in the first song as the first music piece and taking a music piece of the transition time at which the target cut-out time point is positioned in the second song as the second music piece based on the transition time, the target cut-out time point of the first song and the target cut-in time point of the second song; and responding to the first song to be played to the position corresponding to the target cut-out time point, and processing and overlapping the first music section and the second music section based on the song processing parameters.
6. The song playing method according to claim 5, wherein the determining, based on the audio feature information of the first song and the second song, the transition processing parameters of the first music piece corresponding to the target cut-out time point of the first song and the second music piece corresponding to the target cut-in time point of the second song includes: Determining second difference information between the first song and the second song based on the audio feature information of the first song and the audio feature information of the second song; determining the transition time based on second difference information between the first song and the second song; The song processing parameters are determined based on second difference information between the first song and the second song, a target cut-out time point of the first song, and a target cut-in time point of the second song.
7. The song playing method of claim 5, wherein the song processing parameters further comprise a tempo synchronization parameter which adjusts the number of beats per unit time of the first and second pieces of music, the method further comprising; when the beat difference information between the first song and the second song does not exceed a first preset difference threshold, determining the rhythm synchronization parameter as a first preset value, wherein the first preset value is used for indicating that the beat number of unit time of the first music section and the second music section is not adjusted; And when the beat difference information between the first song and the second song exceeds a first preset difference threshold, determining the rhythm synchronization parameter as a second preset value, and adjusting the beat number of the first music section and the second music section in unit time based on the second preset value.
8. A song playing apparatus, the apparatus comprising: The device comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring characteristic information of a first song and a second song, the characteristic information comprises audio characteristic information and structural characteristic information, and the second song is a song played after the first song; A first determining module, configured to determine a candidate cut-out time point of the first song based on the structural feature information of the first song, and determine a candidate cut-in time point of the second song based on the structural feature information of the second song; A second determining module configured to determine a target cut-out time point of the first song from the candidate cut-out time points, and determine a target cut-in time point of the second song from the candidate cut-in time points, based on first difference information of audio feature information of the first song and the second song; A third determining module, configured to determine a transition processing parameter of a first music segment corresponding to a target cut-out time point of the first song and a second music segment corresponding to a target cut-in time point of the second song based on the audio feature information of the first song and the second song; and the processing and playing module is used for responding to the situation that the first song is played to the position corresponding to the target cut-out time point, and processing and playing the first music segment corresponding to the target cut-out time point of the first song and the second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameters.
9. An electronic device comprising a processor and a memory, wherein the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the song playing method of any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that it comprises a computer program for causing an electronic device to execute the steps of the song playing method according to any one of claims 1-7 when said computer program is run on the electronic device.

Description

Song playing method and device, electronic equipment and storage medium Technical Field The present application relates to the field of information processing technologies, and in particular, to a song playing method, apparatus, electronic device, and storage medium. Background In the conventional music playing process, the song a is switched to the song B, so that the song a is often waited for playing to the last second in a natural sequence, and the playing of the song B is started for the first second. In the related mode, the two song linking modes mainly comprise natural transition, namely natural splicing of the tail of the song A and the head of the song B, or energy detection method, which can skip the blank data from the head to the tail and even overlap a part of data to fade in and fade out, so that song switching is more continuous. The related approach may suffer from incomplete stitching, a slightly abrupt hearing or music, resulting in a noticeable hearing fault at the switching instant, disrupting the overall listening experience. Disclosure of Invention The embodiment of the application provides a song playing method, a device, electronic equipment and a storage medium, wherein transition processing parameters of two songs are determined through characteristic information among songs to be joined, so that a seamless joining effect conforming to the characteristics of the songs is realized. In a first aspect, an embodiment of the present application provides a method for playing songs, where the method includes: Acquiring characteristic information of a first song and a second song, wherein the characteristic information comprises audio characteristic information and structural characteristic information, and the second song is a song played after the first song; Determining a candidate cut-out time point of the first song based on the structural feature information of the first song, and determining a candidate cut-in time point of the second song based on the structural feature information of the second song; determining a target cut-out time point of the first song from the candidate cut-out time points based on first difference information of audio feature information of the first song and the second song, and determining a target cut-in time point of the second song from the candidate cut-in time points; Determining transition processing parameters of a first music segment corresponding to a target cut-out time point of the first song and a second music segment corresponding to a target cut-in time point of the second song based on the audio characteristic information of the first song and the second song; and responding to the first song to be played to the position corresponding to the target cut-out time point, and processing and playing a first music segment corresponding to the target cut-out time point of the first song and a second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameters. In a second aspect, an embodiment of the present application provides a song playing apparatus, including: The device comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring characteristic information of a first song and a second song, the characteristic information comprises audio characteristic information and structural characteristic information, and the second song is a song played after the first song; A first determining module, configured to determine a candidate cut-out time point of the first song based on the structural feature information of the first song, and determine a candidate cut-in time point of the second song based on the structural feature information of the second song; A second determining module configured to determine a target cut-out time point of the first song from the candidate cut-out time points, and determine a target cut-in time point of the second song from the candidate cut-in time points, based on first difference information of audio feature information of the first song and the second song; A third determining module, configured to determine a transition processing parameter of a first music segment corresponding to a target cut-out time point of the first song and a second music segment corresponding to a target cut-in time point of the second song based on the audio feature information of the first song and the second song; and the processing and playing module is used for responding to the situation that the first song is played to the position corresponding to the target cut-out time point, and processing and playing the first music segment corresponding to the target cut-out time point of the first song and the second music segment corresponding to the target cut-in time point of the second song based on the transition processing parameters. In a third aspect, an embodiment of the present application further provide