CN111475672B - Lyric distribution method, electronic equipment and storage medium - Google Patents
Lyric distribution method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111475672B CN111475672B CN202010228855.5A CN202010228855A CN111475672B CN 111475672 B CN111475672 B CN 111475672B CN 202010228855 A CN202010228855 A CN 202010228855A CN 111475672 B CN111475672 B CN 111475672B
- Authority
- CN
- China
- Prior art keywords
- singer
- lyrics
- song
- singers
- singed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 18
- 241001342895 Chorus Species 0.000 description 13
- HAORKNGNJCEJBX-UHFFFAOYSA-N cyprodinil Chemical compound N=1C(C)=CC(C2CC2)=NC=1NC1=CC=CC=C1 HAORKNGNJCEJBX-UHFFFAOYSA-N 0.000 description 13
- 230000000694 effects Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/685—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using automatically derived transcript of audio data, e.g. lyrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/632—Query formulation
- G06F16/634—Query by example, e.g. query by humming
Abstract
The embodiment of the invention relates to the field of data processing and discloses a lyric distributing method, electronic equipment and a storage medium. In some embodiments of the present invention, a lyric distributing method includes the following steps: acquiring sound characteristic information of singers; and distributing lyrics of the song to be singed to the singer according to the voice characteristic information of the singer and the audio information of the song to be singed. The embodiment enables the singers to be distributed with lyrics according to the sound characteristics of the singers, and reduces singing difficulty.
Description
Technical Field
The embodiment of the invention relates to the field of data processing, in particular to a lyric distributing method, electronic equipment and a storage medium.
Background
K song is one of the main modes of people's daily life leisure, and people can relax the purpose of recreation in KTV, K song room and even music software through the mode of waiting to sing the song. In the prior art, the functions provided by the K song rooms or music software are mainly as follows: scoring songs sung by the user, and ranking the users according to the scoring result. For example, the entertainment activities that are offered by the current common mini-K-song houses are mainly ranking scores of singing of users singing the same song. In addition, the newly-appearing mini K song rooms can also record songs, and share the recorded songs.
However, the inventors found that there are at least the following problems in the prior art: the user often goes to KTV to make a chorus with a plurality of friends, at this time, the user may often want to sing together with other users, and in this case, the existing chorus room often provides some chorus tracks for the user, and the distribution of chorus paragraphs is implemented according to the singer's difference (or the singer's sex). The original chorus is often a chorus of a plurality of people, and when a user wants to sing a song singed by a single person with friends, the user can only distribute chorus paragraphs by himself, so that the singing effect of the user is poor.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The embodiment of the invention aims to provide a lyric distribution method, electronic equipment and a storage medium, so that lyrics can be distributed to singers according to the sound characteristics of each singer, and the singing difficulty is reduced.
In order to solve the technical problems, the embodiment of the invention provides a lyric distributing method, which comprises the following steps: acquiring sound characteristic information of singers; and distributing lyrics of the song to be singed to the singer according to the voice characteristic information of the singer and the audio information of the song to be singed.
The embodiment of the invention also provides electronic equipment, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the lyric allocation method as mentioned in the above embodiments.
The embodiment of the present invention also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the lyric allocation method mentioned in the above embodiment.
Compared with the prior art, the method and the device for distributing the lyrics of the singer have the advantages that in the lyrics distribution process, the voice characteristic information of the singer and the audio information of the song to be singed are referred, so that the lyrics can be distributed to the singer according to the voice characteristics of each singer, the lyrics distributed to the singer are more suitable for singing of the singer, the singing difficulty is reduced, the singing effect is improved, and the user experience is improved.
In addition, before distributing the lyrics of the song to be sung to the singer according to the voice characteristic information of the singer and the audio information of the song to be sung, the method further comprises the following steps: judging whether the number of singers of the song to be singed is larger than 1; and if the number of the singers is determined to be larger than 1, executing the step of distributing lyrics of the song to be singed for the singers according to the voice characteristic information of the singers and the audio information of the song to be singed.
In addition, if the number of singers is equal to 1, the lyric distribution method further comprises the following steps: and adjusting the tone of the song to be singed according to the voice characteristic information of the singer.
In addition, according to the voice characteristic information of the singer and the audio information of the song to be singed, the lyrics of the song to be singed are distributed for the singer, and the method comprises the following steps: respectively comparing the voice characteristic information of each singer with the audio information of each lyric of the song to be singed, and determining the similarity between the voice characteristic information of each singer and the audio information of each lyric of the song to be singed; and according to the similarity, distributing lyrics of the song to be singed to the singer.
In addition, the voice characteristic information of each singer comprises voice characteristics of N dimensions of the singer, wherein N is an integer greater than 1; respectively comparing the voice characteristic information of each singer with the audio information of each lyric of the song to be singed, and determining the similarity between the voice characteristic information of each singer and the audio information of each lyric of the song to be singed; according to the similarity, assigning lyrics of the song to be singed to the singer comprises: determining the priority of sound features of each dimension; for each lyric of a song to be singed, starting from the sound feature of the dimension with the highest priority, the following comparison operations are sequentially carried out: determining the sound characteristics of lyrics according to the audio information of the lyrics; comparing the sound characteristics of each singer in the dimension with the sound characteristics of the corresponding dimension of the lyrics, and determining the singer with the highest similarity to the sound characteristics of the corresponding dimension of the lyrics; judging whether the number of singers with highest similarity is equal to 1; if the lyrics are determined to be equal to 1, assigning the lyrics to the singer with the highest similarity; if the sound feature is determined to be greater than 1, judging whether the sound feature in the current dimension is the sound feature in the dimension with the lowest priority; if the determination is not, comparing the sound characteristics of the dimension of the next priority; if yes, distributing the lyrics to singers with highest similarity; alternatively, the lyrics are assigned to any one of the singers having the highest similarity.
In addition, after assigning lyrics of a song to be singed to a singer according to the similarity, the method further includes: judging whether singers which are not assigned to lyrics exist or not; and if the song lyrics exist, adjusting the song lyrics distributed to each singer according to a preset adjustment rule, wherein the preset adjustment rule enables each singer to distribute the song lyrics of the song to be singed.
In addition, voice characteristic information of the singer is determined according to the audio data of the singer; the audio data of the singer is the audio data of a historical singing song of the singer and/or the trial singing audio data of the singer.
In addition, the audio data of the singer is the audio data of the historical singing song of the singer, and the voice characteristic information of the singer is obtained, which comprises the following steps: acquiring audio data of a historical singing song of a singer; and analyzing the audio data of the historical singing songs to determine the voice characteristic information of the singer.
In addition, the audio data of the singer is trial singing audio data of the singer, and the lyric distributing method further comprises the following steps: after determining that the singer logs in for the first time, prompting the singer to record trial singing audio; according to the trial singing audio, determining sound characteristic information of singers; the voice characteristic information of the singer is stored.
Drawings
One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which the figures of the drawings are not to be taken in a limiting sense, unless otherwise indicated.
FIG. 1 is a flow diagram of a lyric allocation method according to a first embodiment of the present application;
fig. 2 is a schematic spectrum diagram of a song to be singed according to a first embodiment of the present application;
fig. 3 is a schematic diagram of lyrics display effects of a song to be singed according to a first embodiment of the present application;
FIG. 4 is a flow chart of a lyric allocation method according to a second embodiment of the present application;
fig. 5 is a schematic structural view of an electronic device according to a third embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings. However, those of ordinary skill in the art will understand that in various embodiments of the present application, numerous technical details have been set forth in order to provide a better understanding of the present application. However, the claimed application may be practiced without these specific details and with various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a lyric distribution method which is applied to electronic equipment, such as a server, a cloud server, various mobile terminals and the like. As shown in fig. 1, the lyric allocation method includes:
step 101: and acquiring voice characteristic information of the singer.
Specifically, the electronic device may determine sound characteristic information of each singer by analyzing audio data of a history of singing songs, trial singing audio, and the like of each singer.
In one embodiment, the voice characteristic information of the singer is determined according to the audio data of the singer; the audio data of the singer is the audio data of a historical singing song of the singer and/or the trial singing audio data of the singer.
For example, the audio data of the singer is the audio data of a historical singing song of the singer, and the electronic device acquires the audio data of the historical singing song of the singer; and analyzing the audio data of the historical singing songs to determine the voice characteristic information of the singer.
For example, the electronic device stores audio data of a history singing song of each singer, and when the voice characteristics of the singer need to be analyzed, the electronic device may select one recording audio with the recording time closest to the current time from the audio data of the history singing song of the singer, and analyze the voice characteristics of the singer based on the recording audio. I.e. the audio data of the historically singed song is the last uploaded recorded audio of the terminal used by the singer. When singers singing songs through singing equipment such as music software and a K song room terminal, the singing equipment records audio and uploads the recorded audio to the electronic equipment. The electronic device obtains recorded audio and analyzes the recorded audio to determine sound characteristic information of a singer singing the recorded audio.
When it should be noted, those skilled in the art can understand that, in practical application, the electronic device may also analyze the voice characteristics of the singer based on the audio data of all the historic singing songs of the singer, and the embodiment does not limit the number and selection manners of the analyzed recorded audio.
In another embodiment, the audio data of the singer is trial audio data of the singer, and the electronic device prompts the singer to record the trial audio after determining that the singer is logged in for the first time; according to the trial singing audio, determining sound characteristic information of singers; the voice characteristic information of the singer is stored. For example, the music software may guide the user through a trial audio entry when the user first uses the K-song feature of the music software. The music software can analyze the trial singing audio recorded by the user to determine the sound characteristic information of the user, and the sound characteristic information is associated with the user account number which the user is currently logged in to store. When the user uses the music software again and logs in the user account to make K songs, the music software can directly determine the voice characteristic information of the user according to the user account.
It should be noted that, as will be understood by those skilled in the art, in practical applications, the electronic device may determine the voice feature information of the singer in other ways, which are not listed here.
In one embodiment, the vocal characteristic information of the singer includes an audio frequency of the singer and/or an overtone range of the singer.
It should be noted that, as will be understood by those skilled in the art, in practical application, the voice feature information of the singer may be other voice features of the singer, and this embodiment is merely illustrative.
Step 102: and distributing lyrics of the song to be singed to the singer according to the voice characteristic information of the singer and the audio information of the song to be singed.
Specifically, the electronic device may first obtain the audio information of the song to be singed, and allocate, to each singer, a lyric portion suitable for singing itself based on the voice characteristic information of the singer and the audio information of the song to be singed.
In one embodiment, the electronic device compares the voice characteristic information of each singer with the audio information of each lyric of the song to be singed, and determines the similarity between the voice characteristic information of each singer and the audio information of each lyric of the song to be singed; and according to the similarity, distributing lyrics of the song to be singed to the singer.
In one embodiment, after the assigning the lyrics of the song to be singed to the singer according to the similarity, the electronic device further includes: judging whether singers which are not assigned to lyrics exist or not; and if the song lyrics exist, adjusting the song lyrics distributed to each singer according to a preset adjustment rule, wherein the preset adjustment rule enables each singer to distribute the song lyrics of the song to be singed.
In one embodiment, the preset adjustment rule may be: selecting a first proportion of lyrics from the lyrics of m singers classified to the most lyrics, and distributing the selected lyrics to the singers which are not distributed with the lyrics according to the similarity of the audio information of the selected lyrics and the voice characteristics of the singers which are not distributed with the lyrics aiming at the selected lyrics. In the distribution process, the selected lyrics can be distributed to singers which are not distributed to the lyrics and have highest similarity, other distribution rules can be adopted, and the selected lyrics can be set by a person skilled in the art according to requirements.
In one embodiment, the preset adjustment rule may also be: judging whether the number of singers distributed to the lyrics is 1, if so, determining that the similarity between the lyrics and the audio information of each lyric of the song to be singed is larger than that between the lyrics and the first type of special singers, sequencing the lyrics according to the sequence from large to small of the similarity between the lyrics and the voice characteristic information of the first type of special singers, and reassigning the lyrics ranked at the last preset second proportion. The reassignment principle may be that the reassignment principle is equally assigned to other singers except the first type singer, or that the lyrics to be assigned are assigned to the other singers except the first type singer with the largest similarity based on the voice characteristic information of the other singers except the first type singer and the similarity of the lyrics to be reassigned. After the allocation is completed, whether singers which are not allocated to lyrics exist in the reallocation process is judged again, if so, the allocation process can be reallocated by referring to the steps, and the allocation process can also be directly ended. If not, the lyrics assignment process may be ended. If the number of singers allocated to the lyrics is not 1, judging whether the number of singers not allocated to the lyrics is 1, if so, determining that the second type special singers with the similarity of the audio information of each lyric of the song to be singed is smaller than that of other singers, and sorting the lyrics according to the sequence of the similarity of the voice characteristic information of each lyric and the second type special singers from large to small, and allocating the preset third proportion of lyrics arranged at the forefront to the second type special singers. And if the number of singers which are not allocated to the lyrics is not 1, respectively selecting the lyrics of a fourth proportion from the lyrics of m singers which are classified to the most lyrics, and allocating the selected lyrics to the singers which are not allocated to the lyrics according to the similarity of the audio information of the selected lyrics and the voice characteristics of the singers which are not allocated to the lyrics aiming at the selected lyrics. In the distribution process, the selected lyrics can be distributed to singers which are not distributed to the lyrics and have highest similarity, other distribution rules can be adopted, and the selected lyrics can be set by a person skilled in the art according to requirements.
It should be noted that, as will be understood by those skilled in the art, the first ratio, the second ratio, the third ratio, and the fourth ratio may be set as needed, and the numerical values of the respective ratios are not limited in this embodiment.
It should be noted that, as will be understood by those skilled in the art, in practical application, the preset adjustment rule may be other adjustment rules, where the adjustment rule may be that lyrics is distributed to achieve a chorus effect, and the embodiment does not limit the adjustment rule.
It is worth mentioning that when a special singer exists, lyrics are redistributed, so that the situation that chorus becomes singing due to uneven lyrics distribution caused by the existence of the special singer can be avoided.
For example, the electronic device performs audio analysis on each song in the current singing list to obtain a spectrogram of each song in the singing list. Specifically, the music software may sequentially perform audio analysis on each song in the singing list according to the order of the singing list added in advance by the user, and obtain a spectrogram of each song. For example, the electronic device performs audio analysis on the song "ocean about" in the singing list, i.e., the song to be singed is "ocean about". A schematic spectrum of the song to be singed is shown in fig. 2. The electronic device determines a singing paragraph of each singer according to the sound characteristic information of each singer and the spectrogram of the song, which are determined in step 101.
In one embodiment, the voice characteristic information of each singer includes voice characteristics of N dimensions of the singer, where N is an integer greater than 1. The electronic equipment compares the sound characteristic information of each singer with the audio information of each lyric of the song to be singed respectively, and determines the similarity between the sound characteristic information of each singer and the audio information of each lyric of the song to be singed; according to the similarity, the process of distributing the lyrics of the song to be singed to the singer is as follows:
determining the priority of sound features of each dimension; for each lyric of a song to be singed, starting from the sound feature of the dimension with the highest priority, the following comparison operations are sequentially carried out: determining the sound characteristics of lyrics according to the audio information of the lyrics; comparing the sound characteristics of the dimensions of each singer with the sound characteristics of the dimensions corresponding to the lyrics, and determining the singer with the highest similarity to the sound characteristics of the dimensions corresponding to the lyrics; judging whether the number of singers with highest similarity is equal to 1; if the lyrics are determined to be equal to 1, assigning the lyrics to the singer with the highest similarity; if the sound feature is determined to be greater than 1, judging whether the sound feature in the current dimension is the sound feature in the dimension with the lowest priority; if the determination is not, comparing the sound characteristics of the dimension of the next priority; if yes, distributing the lyrics to singers with highest similarity; alternatively, the lyrics are assigned to any one of the singers having the highest similarity.
It should be noted that, as will be understood by those skilled in the art, the threshold may be set as required, and may be set to any positive number not less than 0 and less than 1, such as 0,0.1, etc., which is not limited herein.
Note that, when the current dimension sound feature is the lowest priority dimension sound feature, the lyrics may be assigned to all singers or the like, and the present embodiment is not limited to this case.
In one example, when the number of singers with the highest similarity is equal to 1, before assigning lyrics to the singers with the highest similarity, the electronic device determines whether the sound feature with the current dimension is the sound feature with the lowest priority, and if it is determined that the sound feature with the current dimension is not the sound feature with the lowest priority, determines whether the threshold corresponding to the sound feature with the highest similarity-next highest similarity > the sound feature with the dimension is satisfied. If the determination is true, a step of assigning lyrics to singers having highest similarity is performed. If the determination is not satisfied, a comparison operation is performed with respect to the sound features of the dimension of the next priority. If the sound characteristic of the current dimension is determined to be the sound characteristic of the dimension with the lowest priority, the lyrics are distributed to the singer with the highest similarity, or the lyrics are distributed to the singer with the highest similarity and the singer with the second highest similarity.
The following illustrates the process of assigning lyrics.
For example, the sound feature information includes sound features of two dimensions, respectively: audio frequency and overtone range. When determining that the two users A and B select to chorus a single song, the electronic device can compare the sound characteristics of the user A and the user B with the original spectrogram of the song to be singed, and distribute lyrics of the song to be singed according to the similarity of the sound characteristics. Assuming that the audio frequency of the user a is similar to the audio frequency of the first sentence originally sung, the user a is allocated to sung the first sentence of lyrics. And assuming that the audio frequency of the user A and the audio frequency of the user B are the same as the original audio frequency, comparing the overtone ranges of the user A and the user B continuously, and allocating which user sings the lyrics when which overtone range of the user is close to the overtone range of the original singing. If the electronic device determines that the similarity between each sentence of lyrics of the user A and the original singing is higher than that of the user B, the electronic device can select 40% of lyrics with the largest difference between the user A and the original singing to be distributed to the user B for singing in order to achieve the chorus effect.
As another example, the sound feature information includes sound features of three dimensions, which are respectively: timbre, audio frequency and overtone range. The priorities of these three dimensions are: tone > audio frequency > overtone range. When it is determined that three users, user a, user B and user C, select to chorus a song, the electronic device determines the timbre of the song from the sound feature of the timbre from the first sentence of lyrics to be singed, and compares the timbre of user a, the timbre of user B and the timbre of user C with the timbre of the lyrics, respectively. The comparison results are in the following cases:
Case 1: there are 1 singer with highest similarity. Assuming that the similarity of the tone color of the user a and the tone color of the lyrics > the similarity of the tone color of the user B and the tone color of the lyrics > the similarity of the tone color of the user C and the tone color of the lyrics, it is explained that the singer having the highest similarity is the user a. In this case, since the tone is not the sound feature of the dimension with the lowest priority, it is determined whether the similarity of the tone of the user a and the tone of the lyrics, the similarity of the tone of the user B and the tone of the lyrics > the preset threshold corresponding to the tone is established; if the determination is true, the first sentence of lyrics is distributed to the user A, if the determination is not true, the electronic equipment determines the audio frequency of the lyrics, and the audio frequency of the user A and the audio frequency of the user B are respectively compared with the audio frequency of the lyrics. There are several cases:
case a: and if the similarity between the audio frequency of the user A and the audio frequency of the lyrics is greater than the similarity between the audio frequency of the user B and the audio frequency of the lyrics, determining the singer with the highest similarity as the user A, wherein the number of the singers with the highest similarity is equal to 1.
Case B: and if the similarity between the audio frequency of the user A and the audio frequency of the lyrics is less than the similarity between the audio frequency of the user B and the audio frequency of the lyrics, determining the singer with the highest similarity as the user B, wherein the number of the singers with the highest similarity is equal to 1.
Case C: similarity of audio frequency of user a and audio frequency of lyrics = similarity of audio frequency of user B and audio frequency of lyrics, determining the singer with the highest similarity as user a and user B, and the number of singers with the highest similarity is equal to 2.
For the case a and the case B, since the audio frequency is not the sound feature of the dimension with the lowest priority, it is required to determine whether the similarity between the audio frequency of the user a and the audio frequency of the lyrics is similar to the similarity between the audio frequency of the user B and the audio frequency of the lyrics, that is, whether the difference is greater than the threshold corresponding to the audio frequency, if so, the lyrics are distributed to the singer with the highest similarity, and if not, it is required to determine based on the sound feature (audio frequency) of the next priority. If, for the case a, judging whether a preset threshold corresponding to the similarity of the audio frequency of the user a and the audio frequency of the lyrics, namely the similarity of the audio frequency of the user B and the audio frequency of the lyrics > the audio frequency is met; if the determination is established, the first sentence of lyrics is allocated to the user A, if the determination is not established, the overtone range of the lyrics is determined, the overtone range of the user A and the overtone range of the lyrics are respectively compared with the overtone range of the lyrics, and since the overtone range is the sound feature of the dimension with the lowest priority, if the similarity of the overtone range of the user A and the overtone range of the lyrics is greater than the similarity of the overtone range of the user B and the overtone range of the lyrics, the singer with the highest similarity is determined to be the user A, the lyrics are allocated to the user A, and if the similarity of the overtone range of the user A and the overtone range of the lyrics is less than the similarity of the overtone range of the lyrics and the overtone range of the lyrics, the singer with the highest similarity is determined to be the user B, and the singer with the highest similarity is allocated to the lyrics.
For the case C, since the number of singers with the highest similarity is greater than 1, and the audio frequency is determined not to be the sound feature of the dimension with the lowest priority, the overtone range of the lyrics is determined, the overtone range of the user a and the overtone range of the lyrics are compared with the overtone range of the lyrics, and since the overtone range is the sound feature of the dimension with the lowest priority, if the similarity of the overtone range of the user a and the overtone range of the lyrics > the similarity of the overtone range of the user B and the overtone range of the lyrics, the singer with the highest similarity is determined to be the user a, the lyrics are assigned to the user a, and if the similarity of the overtone range of the user a and the overtone range of the lyrics < the similarity of the overtone range of the lyrics and the overtone range of the lyrics, the singer with the highest similarity is determined to be the user B, and the lyrics are assigned to the user B.
Case 2: there are multiple singers with highest similarity. Such as similarity of tone color of user a and tone color of lyrics = similarity of tone color of user B and tone color of lyrics > similarity of tone color of user C and tone color of lyrics, or similarity of tone color of user a and tone color of lyrics = similarity of tone color of user B and tone color of lyrics = similarity of tone color of user C and tone color of lyrics. And judging whether the tone is the sound feature with the lowest priority dimension or not because the number of singers with the highest similarity is larger than 1. Since the determination result is not yes, the electronic apparatus performs a comparison operation with respect to the audio frequency. Specifically, the electronic device determines the audio frequency of the lyrics, and compares the audio frequency of user a and the audio frequency of user B with the audio frequency of the lyrics, respectively. The cases where the comparison result exists are similar to case a, case B and case C, and will not be described in detail here. The electronic device performs operations corresponding to the above-mentioned various cases.
In one embodiment, the electronic device adjusts a lyric display file of the song to be sung according to a distribution result of lyrics of the song to be sung after distributing the lyrics of the song to be sung for the singer according to sound characteristic information of the singer and audio information of the song to be sung; the adjusted lyrics display file indicates lyrics assigned to each singer. For example, each lyric is labeled according to the singing users, and the display effect diagram is shown in fig. 3, so that each user is prompted to sing the lyrics in such a display mode.
It is worth mentioning that the song word display file is adjusted, so that singers can know the lyrics singed by the singers, and user experience is improved.
The foregoing is merely illustrative, and is not intended to limit the technical aspects of the present invention.
Compared with the prior art, in the lyric distribution method provided by the embodiment, in the lyric distribution process, the voice characteristic information of the singers and the audio information of the songs to be singed are referred, so that the lyrics can be distributed to the singers according to the voice characteristics of each singer, the lyrics distributed to the singers are more suitable for singing of the singers, the singing difficulty is reduced, the singing effect is improved, and the user experience is improved.
A second embodiment of the present invention relates to a lyric distribution method. The embodiment is further improved on the basis of the first embodiment, and the specific improvement is that: before the lyrics of the song to be sung are distributed for the singer according to the voice characteristic information of the singer and the audio information of the song to be sung, a process for judging whether the number of the singer of the song to be sung is larger than 1 is added.
Specifically, as shown in fig. 4, the present embodiment includes steps 201 to 204, wherein steps 201 and 203 are substantially the same as steps 101 and 102 in the first embodiment, and are not described herein. The differences are mainly described below:
step 201: and acquiring voice characteristic information of the singer.
Step 202: it is determined whether the number of singers of the song to be singed is greater than 1.
Specifically, if it is determined that the number of singers is greater than 1, step 203 is executed, and if it is determined that the number of singers is equal to 1, step 204 is executed.
In one embodiment, the electronic device uses the number of singers in the recorded song last uploaded from the singing terminal used by the singers as the number of singers of the song to be singed.
For example, the process of the electronic device for audio data or trial audio analysis of a historically singed song includes: in the audio collection process, the singing voice of the user is recorded or reproduced through analog equipment to become analog audio, and then the analog audio is digitized to become digital audio, so that audio data are obtained. The electronic equipment takes the digital audio signal as an analysis object, takes digital signal processing as an analysis means, and extracts a series of characteristics of the signal in the time domain and the frequency domain. In particular, audio parsing is mainly implemented using fourier transform and signal sampling techniques. The fourier transform is the basis for performing spectrum analysis, which is to calculate the frequency distribution rule of the amplitude, phase, etc. of the components according to the frequency structure of the signal, and establish a spectrogram with the frequency as the horizontal axis. Since the timbre determines the auditory effect of the sound heard by people, people often distinguish the sounds of different people through the timbre, and since the frequency spectrums of the sounds of different timbres are different, the electronic device can determine whether the analyzed section of audio contains multiple singers according to the spectrogram obtained by audio analysis of the recorded song.
In this embodiment, the process of determining the number of singers is used as a subsequent step of obtaining the voice feature information of the singers, and in practical application, the process of determining the number of singers may also be used as a previous step of step 201, for example, the electronic device determines the number of singers of the song to be singed according to the number of singers input or selected by the singer at the singing terminal used, or determines the number of singers according to the number of currently logged users, and obtains the voice feature information of each singer after determining the singers. For example, if the number of singers input or selected by the singer at the singing terminal used is 3, it is determined that the number of singers of the song to be singed is 3.
It should be noted that, in practical applications, those skilled in the art may determine the number of singers by other ways, and the present embodiment is merely illustrative.
Step 203: and distributing lyrics of the song to be singed to the singer according to the voice characteristic information of the singer and the audio information of the song to be singed. The flow is then ended.
Step 204: and adjusting the tone of the song to be singed according to the voice characteristic information of the singer.
Specifically, when it is determined that there are only 1 singers, the song to be singed may be adjusted according to the voice characteristic information of the singers, such as the breath length, the pitch, etc., for example, the tone of the treble portion of the song may be appropriately reduced according to the pitch of the user, so as to reduce the singing pressure of the user.
It is worth mentioning that when a single singer sings, the tone of the song to be singed is adjusted according to the voice characteristic information of the singer, so that the singing pressure of the user can be reduced.
It should be noted that, it should be understood by those skilled in the art that the step 204 is not an essential step in the present embodiment, and in practical applications, those skilled in the art may selectively perform the step 204 as required, that is, when there are only 1 singer, the tone of the song to be singed may not be adjusted.
The following illustrates the procedure of the song assignment method in connection with the actual scenario.
Step 301: when a user sings a song by using an audio collection device (such as a device in KTV, a device in a K song room or music software with a K song function), the audio collection device collects the audio of the song singed by the user and uploads the collected audio to the electronic device.
Specifically, when a user uses KTV (or a K song room) to perform K songs, an audio collection device (such as a microphone) of the KTV or the K song room can collect songs sung by the user, and upload the collected songs to the electronic device. Or the user can also establish connection with the KTV network by scanning the two-dimensional codes of the room, receive the audio information acquired by the KTV equipment through the terminal, and upload the received audio information to the electronic equipment of the music software.
When the user sings the song by using the music software with the K song function, the audio collection can be carried out on the song singed by the user through the music software, and the collected song is directly uploaded to the electronic equipment of the music software.
Step 302: and the electronic equipment analyzes the received audio, and judges whether more than one singer exists currently according to the audio analysis result. When the determination result is yes, step 303 is executed; when the judgment result is negative, executing step 306;
In the audio collection process, the singing voice of the user is recorded or reproduced through the analog equipment to become analog audio, and then the analog audio is digitized to become digital audio, so that the audio data uploaded to the electronic equipment is finally obtained. The audio analysis is a process of extracting a series of characteristics of a signal in the time domain and the frequency domain by taking a digital audio signal as an analysis object and digital signal processing as an analysis means. Audio parsing is mainly implemented using fourier transform and signal sampling techniques. The fourier transform is the basis for performing spectrum analysis, which is to calculate the frequency distribution rule of the amplitude, phase, etc. of the components according to the frequency structure of the signal, and establish a spectrogram with the frequency as the horizontal axis. Since the tone color determines the auditory effect that people hear sounds, people often distinguish sounds of different people through the tone color. Because the spectra of different audio sounds are different, the electronic device can determine whether the analyzed piece of audio contains multiple singers based on the spectrograms obtained by the audio analysis.
Step 303: the electronic device may confirm the sound characteristics of the individual singers, respectively.
Specifically, in the present solution, the electronic device may record the audio frequencies and overtones ranges of the identified plurality of users.
For example, the music software may guide the user through a trial audio entry when the user first uses the K-song feature of the music software. The music software can analyze the trial singing audio recorded by the user to determine the sound characteristics of the user, and the sound characteristics are associated with and stored in the user account currently logged in by the user, so that when the user logs in the user account again by using the music software to perform K songs, the music software can directly determine the sound characteristics of the user according to the user account.
Step 304: and carrying out audio analysis on each song in the current singing list in sequence to obtain a spectrogram of each song in the singing list.
Specifically, the electronic device may sequentially perform audio analysis on each song in the singing list according to the order of the singing list added in advance by the user, and obtain a spectrogram of each song.
Step 305: the performance paragraph of each singer is determined based on the sound characteristics of each singer determined by performing step 303 and the spectrogram of the song determined by performing step 304. The flow is then ended.
For example, when it is determined that there are two users, user a and user B, selecting a single song, by performing step 303, the voice characteristics of the two users may be compared with the spectrogram of the original song, and the allocation of singing lyrics may be performed according to the similarity of the audio characteristics. If the voice characteristics of the user A are similar to the frequency of the original singing first sentence, distributing the singing first sentence lyrics of the user A; and assuming that the voice frequency and the original singing frequency of the user A and the user B are the same, comparing the overtone ranges of the user A and the user B continuously, and assigning which user sings the lyrics when which overtone range of the user is close to the overtone range of the original singing. And when judging that the similarity between each sentence of lyrics of the user A and the original singing is higher than that of the user B, in order to achieve the chorus effect, the music software can select 40% of lyrics with the largest difference between the user A and the original singing to be distributed to the user B for singing.
Meanwhile, in order to facilitate prompting the lyrics to be singed to the user, in the scheme, the music software can mark each sentence of lyrics according to different singing users when displaying the lyrics, so as to prompt each user of the lyrics to be singed in the display mode.
Step 306: songs in the singing list are adjusted according to the voice characteristics of the user.
Specifically, the electronic device adjusts according to the voice characteristics of the user, such as voice frequency, tone level, etc., and other ordered songs in the singing list, such as according to the pitch of the user, and can appropriately reduce the tone of the treble part of the song to reduce the singing pressure of the user.
The foregoing is merely illustrative, and is not intended to limit the technical aspects of the present invention.
Compared with the prior art, in the lyric distribution method provided by the embodiment, in the lyric distribution process, the voice characteristic information of the singers and the audio information of the songs to be singed are referred, so that the lyrics can be distributed to the singers according to the voice characteristics of each singer, the lyrics distributed to the singers are more suitable for singing of the singers, the singing difficulty is reduced, the singing effect is improved, and the user experience is improved. In addition, before lyrics are distributed, the number of singers is judged, and resource waste caused by starting lyrics distribution under the condition of singing by a single person is avoided.
The above steps of the methods are divided, for clarity of description, and may be combined into one step or split into multiple steps when implemented, so long as they include the same logic relationship, and they are all within the protection scope of this patent; it is within the scope of this patent to add insignificant modifications to the algorithm or flow or introduce insignificant designs, but not to alter the core design of its algorithm and flow.
A third embodiment of the present invention relates to an electronic device, as shown in fig. 5, including: at least one processor 401; and a memory 402 communicatively coupled to the at least one processor 401; wherein the memory 402 stores instructions executable by the at least one processor 401, the instructions being executable by the at least one processor 401 to enable the at least one processor 401 to perform the lyrics assigning method as mentioned in the above embodiments.
The electronic device includes: one or more processors 401, and a memory 402, one processor 401 being illustrated in fig. 5. The processor 401, the memory 402 may be connected by a bus or otherwise, in fig. 5 by way of example. Memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 401 executes various functional applications of the apparatus and data processing, i.e., implements the above-described lyrics assignment method, by running nonvolatile software programs, instructions, and modules stored in the memory 402.
Memory 402 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store a list of options, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some implementations, the memory 402 may optionally include memory located remotely from the processor 401, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in memory 402 that, when executed by one or more processors 401, perform the lyrics assignment method in any of the method embodiments described above.
The above product may perform the method provided by the embodiment of the present application, and has the corresponding functional module and beneficial effect of the performing method, and technical details not described in detail in the embodiment of the present application may be referred to the method provided by the embodiment of the present application.
A fourth embodiment of the present application relates to a computer-readable storage medium storing a computer program. The computer program implements the above-described method embodiments when executed by a processor.
That is, it will be understood by those skilled in the art that all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program stored in a storage medium, where the program includes several instructions for causing a device (which may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples of carrying out the application and that various changes in form and details may be made therein without departing from the spirit and scope of the application.
Claims (8)
1. A lyric distributing method, comprising:
acquiring sound characteristic information of singers;
Distributing lyrics of the song to be singed to the singer according to the sound characteristic information of the singer and the audio information of the song to be singed;
the voice characteristic information of each singer comprises voice characteristics of N dimensions of the singer, wherein N is an integer greater than 1; sound features of each dimension have priority;
the distributing the lyrics of the song to be singed for the singer according to the voice characteristic information of the singer and the audio information of the song to be singed comprises the following steps:
determining the priority of sound features of each dimension;
for each lyric of the song to be singed, starting from the sound feature of the dimension with the highest priority, the following comparison operations are sequentially carried out:
determining the sound characteristics of the lyrics according to the audio information of the lyrics;
comparing the sound characteristics of the dimensions of each singer with the sound characteristics of the dimensions corresponding to the lyrics to determine the singer with the highest similarity to the sound characteristics of the dimensions corresponding to the lyrics;
judging whether the number of singers with highest similarity is equal to 1;
if the lyrics are determined to be equal to 1, distributing the lyrics to singers with highest similarity;
If the sound feature is determined to be greater than 1, judging whether the sound feature in the current dimension is the sound feature in the dimension with the lowest priority; if the determination is not, comparing the sound characteristics of the dimension of the next priority; if yes, distributing the lyrics to singers with highest similarity; or, assigning lyrics to any one of the singers with highest similarity.
2. The lyric assignment method of claim 1, further comprising, before assigning lyrics of the singing song to the singer based on sound characteristic information of the singer and audio information of the singing song:
judging whether the number of singers of the song to be singed is larger than 1;
and if the number of the singers is determined to be larger than 1, executing the step of distributing lyrics of the song to be singed for the singers according to the sound characteristic information of the singers and the audio information of the song to be singed.
3. The lyrics distribution method of claim 2, wherein if it is determined that the number of singers is equal to 1, the lyrics distribution method further comprises:
and adjusting the tone of the song to be singed according to the voice characteristic information of the singer.
4. The lyric allocation method of claim 1, further comprising, after the allocation of the lyrics of the song to be singed to the singer according to the similarity:
judging whether singers which are not assigned to lyrics exist or not;
and if the song lyrics exist, adjusting the song lyrics distributed to each singer according to a preset adjustment rule, wherein the preset adjustment rule enables each singer to distribute the song lyrics of the song to be singed.
5. The lyrics distribution method of claim 1 or 2, wherein the voice characteristic information of the singer is determined according to audio data of the singer; the audio data of the singer is the audio data of the historical singing songs of the singer and/or the trial singing audio data of the singer.
6. The lyric distribution method of claim 5, wherein the singer's audio data is a singing trial audio data of the singer, the lyric distribution method further comprising:
after determining that the singer logs in for the first time, prompting the singer to record trial singing audio;
determining sound characteristic information of the singer according to the trial singing audio;
And storing the voice characteristic information of the singer.
7. An electronic device, comprising: at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the lyric assignment method of any of claims 1 to 6.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the lyric allocation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228855.5A CN111475672B (en) | 2020-03-27 | 2020-03-27 | Lyric distribution method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010228855.5A CN111475672B (en) | 2020-03-27 | 2020-03-27 | Lyric distribution method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111475672A CN111475672A (en) | 2020-07-31 |
| CN111475672B true CN111475672B (en) | 2023-12-08 |
Family
ID=71747836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010228855.5A Active CN111475672B (en) | 2020-03-27 | 2020-03-27 | Lyric distribution method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111475672B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008003483A (en) * | 2006-06-26 | 2008-01-10 | Taito Corp | Karaoke device |
| CN102915725A (en) * | 2012-09-10 | 2013-02-06 | 福建星网视易信息系统有限公司 | Human-computer interaction song singing system and method |
| JP2015011245A (en) * | 2013-06-29 | 2015-01-19 | 株式会社第一興商 | Karaoke system corresponding to singing-by-section |
| JP2015045671A (en) * | 2013-08-27 | 2015-03-12 | 株式会社第一興商 | Singing part decision system |
| CN104966527A (en) * | 2015-05-27 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Karaoke processing method, apparatus, and system |
| CN105023559A (en) * | 2015-05-27 | 2015-11-04 | 腾讯科技（深圳）有限公司 | Karaoke processing method and system |
| CN105868397A (en) * | 2016-04-19 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Method and device for determining song |
| CN106991163A (en) * | 2017-03-31 | 2017-07-28 | 福州大学 | A kind of song recommendations method based on singer's sound speciality |
| CN107093419A (en) * | 2016-02-17 | 2017-08-25 | 广州酷狗计算机科技有限公司 | A kind of dynamic vocal accompaniment method and apparatus |
| CN108630240A (en) * | 2017-03-23 | 2018-10-09 | 北京小唱科技有限公司 | A kind of chorus method and device |
| CN109102800A (en) * | 2018-07-26 | 2018-12-28 | 广州酷狗计算机科技有限公司 | A kind of method and apparatus that the determining lyrics show data |
| CN109272975A (en) * | 2018-08-14 | 2019-01-25 | 无锡冰河计算机科技发展有限公司 | Sing accompaniment automatic adjusting method, device and KTV jukebox |
| CN109448754A (en) * | 2018-09-07 | 2019-03-08 | 南京光辉互动网络科技股份有限公司 | A kind of various dimensions singing marking system |
| JP6547878B1 (en) * | 2018-06-21 | 2019-07-24 | カシオ計算機株式会社 | Electronic musical instrument, control method of electronic musical instrument, and program |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6610714B1 (en) * | 2018-06-21 | 2019-11-27 | カシオ計算機株式会社 | Electronic musical instrument, electronic musical instrument control method, and program |
-
2020
- 2020-03-27 CN CN202010228855.5A patent/CN111475672B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008003483A (en) * | 2006-06-26 | 2008-01-10 | Taito Corp | Karaoke device |
| CN102915725A (en) * | 2012-09-10 | 2013-02-06 | 福建星网视易信息系统有限公司 | Human-computer interaction song singing system and method |
| JP2015011245A (en) * | 2013-06-29 | 2015-01-19 | 株式会社第一興商 | Karaoke system corresponding to singing-by-section |
| JP2015045671A (en) * | 2013-08-27 | 2015-03-12 | 株式会社第一興商 | Singing part decision system |
| CN104966527A (en) * | 2015-05-27 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Karaoke processing method, apparatus, and system |
| CN105023559A (en) * | 2015-05-27 | 2015-11-04 | 腾讯科技（深圳）有限公司 | Karaoke processing method and system |
| CN107093419A (en) * | 2016-02-17 | 2017-08-25 | 广州酷狗计算机科技有限公司 | A kind of dynamic vocal accompaniment method and apparatus |
| CN105868397A (en) * | 2016-04-19 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Method and device for determining song |
| CN108630240A (en) * | 2017-03-23 | 2018-10-09 | 北京小唱科技有限公司 | A kind of chorus method and device |
| CN106991163A (en) * | 2017-03-31 | 2017-07-28 | 福州大学 | A kind of song recommendations method based on singer's sound speciality |
| JP6547878B1 (en) * | 2018-06-21 | 2019-07-24 | カシオ計算機株式会社 | Electronic musical instrument, control method of electronic musical instrument, and program |
| CN109102800A (en) * | 2018-07-26 | 2018-12-28 | 广州酷狗计算机科技有限公司 | A kind of method and apparatus that the determining lyrics show data |
| CN109272975A (en) * | 2018-08-14 | 2019-01-25 | 无锡冰河计算机科技发展有限公司 | Sing accompaniment automatic adjusting method, device and KTV jukebox |
| CN109448754A (en) * | 2018-09-07 | 2019-03-08 | 南京光辉互动网络科技股份有限公司 | A kind of various dimensions singing marking system |
Non-Patent Citations (3)
| Title |
|---|
| Singing voice identification and lyrics transcription for music information retrieval invited paper;Annamaria Mesaros;《2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)》;全文 * |
| 卡拉OK评分系统的应用研究;刘旺;;电脑知识与技术(第11期);全文 * |
| 演唱者声音特质建模及其应用;苏金池;《CNKI》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111475672A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108074557B (en) | Tone adjusting method, device and storage medium | |
| CN110019931B (en) | Audio classification method and device, intelligent equipment and storage medium | |
| US9532136B2 (en) | Semantic audio track mixer | |
| KR101249024B1 (en) | Method and electronic device for determining a characteristic of a content item | |
| US8865993B2 (en) | Musical composition processing system for processing musical composition for energy level and related methods | |
| CN103971689A (en) | Audio identification method and device | |
| CN108766407B (en) | Audio connection method and device | |
| KR101917216B1 (en) | Vocal Evaluating System | |
| US20190199781A1 (en) | Music categorization using rhythm, texture and pitch | |
| US11271993B2 (en) | Streaming music categorization using rhythm, texture and pitch | |
| WO2015114216A2 (en) | Audio signal analysis | |
| Niyazov et al. | Content-based music recommendation system | |
| Venkatesh et al. | Artificially synthesising data for audio classification and segmentation to improve speech and music detection in radio broadcast | |
| CN112489610B (en) | Intelligent chorus method and device | |
| CN111475672B (en) | Lyric distribution method, electronic equipment and storage medium | |
| JP2008216486A (en) | Music reproduction system | |
| KR101813704B1 (en) | Analyzing Device and Method for User's Voice Tone | |
| Jensen et al. | Binary decision tree classification of musical sounds | |
| CN107025902B (en) | Data processing method and device | |
| CN109754820B (en) | Target audio acquisition method and device, storage medium and terminal | |
| JP2023539121A (en) | Audio content identification | |
| CN114078464B (en) | Audio processing method, device and equipment | |
| CN111370013A (en) | Automatic sound migration method and system and storage medium | |
| US11609948B2 (en) | Music streaming, playlist creation and streaming architecture | |
| JP5272141B2 (en) | Voice processing apparatus and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |