CN104810025A - Audio similarity detecting method and device - Google Patents
Audio similarity detecting method and device Download PDFInfo
- Publication number
- CN104810025A CN104810025A CN201510148926.XA CN201510148926A CN104810025A CN 104810025 A CN104810025 A CN 104810025A CN 201510148926 A CN201510148926 A CN 201510148926A CN 104810025 A CN104810025 A CN 104810025A
- Authority
- CN
- China
- Prior art keywords
- eigenwert
- evaluated
- audio signal
- time sequence
- sound signal
- 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.)
- Granted
Links
Abstract
The invention relates to an audio similarity detecting method and device. The method comprises the steps of acquiring an audio signal to be evaluated; obtaining an audio signal spectrum according to the audio signal to be evaluated; recognizing the peak position of the audio signal spectrum; acquiring the feature value and time point corresponding to the peak position; obtaining a first time sequence of the audio signal to be evaluated according to each feature value and the time point; comparing the first time sequence with a second time sequence; obtaining the similarity of the audio signal to be evaluated and the reference audio signal according to the comparison result, wherein the second time sequence is the pre-obtained time sequence of the reference audio signal corresponding to the audio signal to be evaluated. With the adoption of the method and the device, the audio signal can be quickly and accurately evaluated; the method and the device can be applied to various application scenes.
Description
Technical field
The present invention relates to audio signal processing technique field, particularly relate to a kind of audio similarity detection method, audio similarity pick-up unit.
Background technology
Along with the development of scientific and technological level, people can obtain the television datas such as song by all means.Under the rhythm of life day by day accelerated, people have been not content with the simple appreciation to television data, but recreate by oneself by imitating the modes such as song, the object loosened to reach body and mind, reduce pressure.In addition, in a lot of place, such as, singing match etc., need the quality judging that user sings, evaluating with regard to needing the song to player or user sing.But in prior art, people are merely able to the impression according to self or other people, judge the audio similarity in process of imitation roughly, cause the accuracy of audio similarity judged result not high.
Summary of the invention
Based on this, be necessary for the problems referred to above, a kind of audio similarity detection method and device be provided, the accurate evaluation of audio similarity can be realized.
A kind of audio similarity detection method, comprises step:
Obtain sound signal to be evaluated, obtain audio signal frequency spectrum according to described sound signal to be evaluated;
Identify the crest location of described audio signal frequency spectrum;
Obtain each described crest location characteristic of correspondence value and time point, obtain the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
Described very first time sequence and the second time series are contrasted, obtain the similarity of sound signal to be evaluated and reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
A kind of audio similarity pick-up unit, comprising:
Audio signal frequency spectrum determination module, for obtaining sound signal to be evaluated, obtains audio signal frequency spectrum according to described sound signal to be evaluated;
Crest location identification module, for identifying the crest location of described audio signal frequency spectrum;
Very first time sequence determination module, for obtaining each described crest location characteristic of correspondence value and time point, obtains the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
Similarity detection module, for described very first time sequence and the second time series are contrasted, obtain the similarity of sound signal to be evaluated and described reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
Audio similarity detection method of the present invention and device, sound signal to be evaluated is processed, obtain audio signal frequency spectrum, identify the crest location of audio signal frequency spectrum, and record each crest location characteristic of correspondence value and time point, form the very first time sequence of sound signal to be evaluated, then the second time series of very first time sequence and reference audio signal is carried out similarity analysis, obtain the similarity of sound signal to be evaluated according to similarity analysis result.The present invention can evaluate fast and accurately to sound signal, can be applied to plurality of application scenes.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the inventive method embodiment;
Fig. 2 is the structural representation of apparatus of the present invention embodiment;
Fig. 3 is the structural representation of audio signal frequency spectrum determination module embodiment of the present invention;
Fig. 4 is the structural representation of similarity detection module embodiment of the present invention.
Embodiment
The technical matters solved for a better understanding of the present invention, the technical scheme taked and the technique effect reached, be described in detail below in conjunction with the embodiment of accompanying drawing to audio similarity detection method of the present invention and device.
As shown in Figure 1, a kind of audio similarity detection method, comprises step:
S110, obtain sound signal to be evaluated, obtain audio signal frequency spectrum according to described sound signal to be evaluated;
S120, identify the crest location of described audio signal frequency spectrum;
S130, obtain each described crest location characteristic of correspondence value and time point, obtain the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
S140, described very first time sequence and the second time series to be contrasted, obtain the similarity of sound signal to be evaluated and reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
Carry out recording sampling to user's audio frequency such as to give song recitals, obtain the sound signal of segmentation, the sample frequency of sampling of wherein recording can set according to concrete demand.In order to realize the Fast Evaluation of sound signal similarity, only wherein as sound signal to be evaluated, this section audio signal and corresponding reference audio signal can will be carried out similarity analysis by a section audio signal.
After getting sound signal to be evaluated, need sound signal to be evaluated to process, obtain audio signal frequency spectrum, so that follow-up similarity analysis.In one embodiment, the step obtaining audio signal frequency spectrum according to described sound signal to be evaluated in step S110 can comprise:
S1101, to described sound signal to be evaluated go interference;
S1102, to go disturb after sound signal to be evaluated carry out framing, pre-emphasis, add the bright window of Hamming and Fourier transform, obtain audio signal frequency spectrum.
Interference process, framing, pre-emphasis are gone to sound signal, adding Hamming bright window process and Fourier transform all can by method realization existing in prior art.
After obtaining audio signal frequency spectrum, namely can identify the crest location in this audio signal frequency spectrum, and obtain each crest location characteristic of correspondence value and time point.The time point that each eigenwert correspondence one is unique, these eigenwerts form the time series of sound signal to be evaluated with corresponding time point.It should be noted that, the second time series can obtain according to the above-mentioned method obtaining very first time sequence identical; Very first time sequence and the second time series only in order to the time series of the time series or reference audio signal of distinguishing sound signal to be evaluated, are not limited seasonal effect in time series order etc.
According to very first time sequence and the second time series, the similarity analysis of sound signal to be evaluated namely can be carried out.In one embodiment, described very first time sequence and the second time series are contrasted in step S140, the step obtaining the similarity of sound signal to be evaluated and reference audio signal according to comparing result comprises:
S1401, order according to the eigenwert in very first time sequence, in very first time sequence an one selected eigenwert is mated with each eigenwert in the second time series, judges in described second time series, whether there is the eigenwert of mating with described selected eigenwert;
If S1402 has, determine the mistiming of the time point that time point corresponding to the eigenwert of described coupling is corresponding with described selected eigenwert, described selected eigenwert and each time point corresponding to the follow-up each eigenwert of described selected eigenwert are all added the described mistiming, when the described mistiming is less than predetermined threshold value, the number that eigenwert is mated is added 1, and using the next eigenwert of described selected eigenwert as new selected eigenwert, return step S1401;
If S1403 does not have, using the next eigenwert of the described selected eigenwert in very first time sequence as new selected eigenwert, return step S1401;
S1404, after each selected eigenwert in very first time sequence has been mated with each eigenwert in the second time series, according to the number that the eigenwert in very first time sequence is mated with the eigenwert in the second time series, obtain the similarity of sound signal to be evaluated and reference audio signal.
In order to better understand the process of above-mentioned similarity analysis, be described in detail below.
S1, the eigenwert of first in very first time sequence to be mated with each eigenwert in the second time series, have in the second time series during the eigenwert of mating with first eigenwert and enter step S2, otherwise enter S3.Wherein mate the similarity referring to two eigenwerts and be greater than predetermined threshold value, there is similarity.
S2, the eigenwert of calculating coupling and the mistiming of first eigenwert, time point corresponding for each eigenwert after the eigenwert of first in very first time sequence and first eigenwert is all added the described mistiming.If the described mistiming is less than predetermined threshold value, be then judged as in the second time series, there is the eigenwert of mating with first eigenwert, the number that eigenwert is mated is added 1, otherwise be judged to be in the second time series the eigenwert of mating with first eigenwert.Then step S3 is entered.
S3, the eigenwert of second in very first time sequence to be mated with each eigenwert in the second time series.Have in the second time series during the eigenwert of mating with second eigenwert and enter step S4, otherwise enter S5.
S4, the eigenwert of calculating coupling and the mistiming of second eigenwert, time point corresponding for each eigenwert after the eigenwert of second in very first time sequence and second eigenwert is all added the described mistiming.If the described mistiming is less than predetermined threshold value, be then judged as in the second time series, there is the eigenwert of mating with second eigenwert, the number that eigenwert is mated is added 1, otherwise be judged to be in the second time series the eigenwert of mating with second eigenwert.Enter step S5.
S5, the eigenwert of the 3rd in very first time sequence to be mated with each eigenwert in the second time series.
……
According to the method described above, after all eigenwerts in very first time sequence have been mated, according to the number of the matching characteristic value of record, namely can treat the similarity evaluating audio frequency and evaluate.
Audio frequency to be evaluated may occur leaking the situation of sound, and the quantity of the eigenwert in the quantity of the eigenwert namely in very first time sequence and the second time series is unequal.So when evaluating the similarity of audio frequency to be evaluated, it is also conceivable to the number of Lou sound.The method of leaking sound judgement is: certain eigenwert in very first time sequence mated with each eigenwert in the second time series, if certain eigenwert in very first time sequence is not mated with the eigenwert in the second time series of corresponding order, and both similarities do not meet predetermined threshold value, but a certain eigenwert after the ordinal characteristics value corresponding to the second time series of this eigenwert in very first time sequence is mated, then illustrate that sound is leaked in appearance at this eigenwert place of very first time sequence.Such as, second eigenwert in very first time sequence is not mated with the eigenwert of second in the second time series, but second eigenwert in very first time sequence is mated with the eigenwert of the 3rd in the second time series, then illustrate that second eigenwert place in very first time sequence occurs leaking sound.Now the number of leaking sound can be added 1.After each eigenwert of very first time sequence has been mated, according to the leakage number of sound and the number of matching characteristic value, the similarity of sound signal to be evaluated is evaluated.
Based on same inventive concept, the present invention also provides a kind of audio similarity pick-up unit, is described in detail below in conjunction with the embodiment of accompanying drawing to apparatus of the present invention.
As shown in Figure 2, a kind of audio similarity pick-up unit, comprising:
Audio signal frequency spectrum determination module 210, for obtaining sound signal to be evaluated, obtains audio signal frequency spectrum according to described sound signal to be evaluated;
Crest location identification module 220, for identifying the crest location of described audio signal frequency spectrum;
Very first time sequence determination module 230, for obtaining each described crest location characteristic of correspondence value and time point, obtains the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
Similarity detection module 240, for described very first time sequence and the second time series are contrasted, obtain the similarity of sound signal to be evaluated and described reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
In order to realize the Fast Evaluation of sound signal similarity, audio signal frequency spectrum determination module 210 can only using intercepting one section audio signal as sound signal to be evaluated.After audio signal frequency spectrum determination module 210 gets sound signal to be evaluated, need sound signal to be evaluated to process, obtain audio signal frequency spectrum, so that follow-up similarity analysis.As shown in Figure 3, described audio signal frequency spectrum determination module 210 can comprise:
Go interference units 2101, for going interference to described sound signal to be evaluated;
Audio signal frequency spectrum determining unit 2102, for going the sound signal to be evaluated after disturbing to carry out framing, pre-emphasis, add the bright window of Hamming and Fourier transform, obtains audio signal frequency spectrum.
Go interference units 2101 pairs of sound signals to go interference process, audio signal frequency spectrum determining unit 2102 is carried out framing, pre-emphasis to going the sound signal after disturbing, is added Hamming bright window process and Fourier transform all can be realized by mode existing in prior art.
After audio signal frequency spectrum determination module 210 obtains audio signal frequency spectrum, crest location identification module 220 identifies the crest location of audio signal frequency spectrum.Very first time sequence determination module 230 obtains each crest location characteristic of correspondence value and time point, obtains the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point.Namely very first time sequence and the second time series obtained in advance can be carried out similarity analysis by similarity detection module 240.
As shown in Figure 4, described similarity detection module 240 can comprise:
Matching unit 2401, for the order according to the eigenwert in very first time sequence, in very first time sequence an one selected eigenwert is mated with each eigenwert in the second time series, judges in described second time series, whether there is the eigenwert of mating with described selected eigenwert;
Revise and counting unit 2402, for when there being the eigenwert of coupling, determine the mistiming of the time point that time point corresponding to the eigenwert of described coupling is corresponding with described selected eigenwert, described selected eigenwert and each time point corresponding to the follow-up each eigenwert of described selected eigenwert are all added the described mistiming, when the described mistiming is less than predetermined threshold value, the number that eigenwert is mated is added 1, and using the next eigenwert of described selected eigenwert as new described selected eigenwert, described matching unit 2401 continues to mate new described selected eigenwert,
Eigenwert selectes unit 2403, for when there is no the eigenwert of mating, using the next eigenwert of the described selected eigenwert in very first time sequence as new described selected eigenwert, described matching unit 2401 continues to mate new described selected eigenwert;
Similarity detecting unit 2404, for after each selected eigenwert in very first time sequence has been mated with each eigenwert in the second time series, according to the number that the eigenwert in very first time sequence is mated with the eigenwert in the second time series, obtain the similarity of sound signal to be evaluated and reference audio signal.
Other technical characteristic of apparatus of the present invention is identical with the inventive method, does not repeat them here.
The present invention can evaluate accurately to sound signal; Sample segment analysis can be carried out to sound signal, analyze compared to entirety, accelerate analytic process.Therefore, the present invention has taken into account speed and the accuracy of sound signal evaluation, namely can evaluate accurately and rapidly sound signal, can be applied to plurality of application scenes.
Each technical characteristic of the above embodiment can combine arbitrarily, for making description succinct, the all possible combination of each technical characteristic in above-described embodiment is not all described, but, as long as the combination of these technical characteristics does not exist contradiction, be all considered to be the scope that this instructions is recorded.
The above embodiment only have expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be construed as limiting the scope of the patent.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (6)
1. an audio similarity detection method, is characterized in that, comprises step:
Obtain sound signal to be evaluated, obtain audio signal frequency spectrum according to described sound signal to be evaluated;
Identify the crest location of described audio signal frequency spectrum;
Obtain each described crest location characteristic of correspondence value and time point, obtain the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
Described very first time sequence and the second time series are contrasted, obtain the similarity of sound signal to be evaluated and reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
2. audio similarity detection method according to claim 1, is characterized in that, described very first time sequence and the second time series are contrasted, the step obtaining the similarity of sound signal to be evaluated and reference audio signal according to comparing result comprises:
According to the order of the eigenwert in very first time sequence, the selected eigenwert of in very first time sequence is mated with each eigenwert in the second time series, judge in described second time series, whether there is the eigenwert of mating with described selected eigenwert;
If have, determine the mistiming of the time point that time point corresponding to the eigenwert of described coupling is corresponding with described selected eigenwert, described selected eigenwert and each time point corresponding to the follow-up each eigenwert of described selected eigenwert are all added the described mistiming, when the described mistiming is less than predetermined threshold value, the number that eigenwert is mated is added 1, and using the next eigenwert of described selected eigenwert as new selected eigenwert, return the order according to the eigenwert in very first time sequence, in very first time sequence an one selected eigenwert and each eigenwert in the second time series are carried out the step of mating,
If do not have, using the next eigenwert of the described selected eigenwert in very first time sequence as new selected eigenwert, return the order according to the eigenwert in very first time sequence, the selected eigenwert of in very first time sequence and each eigenwert in the second time series are carried out the step of mating;
After each selected eigenwert in very first time sequence has been mated with each eigenwert in the second time series, according to the number that the eigenwert in very first time sequence is mated with the eigenwert in the second time series, obtain the similarity of sound signal to be evaluated and reference audio signal.
3. audio similarity detection method according to claim 1 and 2, is characterized in that, comprises according to the step that described sound signal to be evaluated obtains audio signal frequency spectrum:
Interference is gone to described sound signal to be evaluated;
To going the sound signal to be evaluated after disturbing to carry out framing, pre-emphasis, add the bright window of Hamming and Fourier transform, obtain audio signal frequency spectrum.
4. an audio similarity pick-up unit, is characterized in that, comprising:
Audio signal frequency spectrum determination module, for obtaining sound signal to be evaluated, obtains audio signal frequency spectrum according to described sound signal to be evaluated;
Crest location identification module, for identifying the crest location of described audio signal frequency spectrum;
Very first time sequence determination module, for obtaining each described crest location characteristic of correspondence value and time point, obtains the very first time sequence of sound signal to be evaluated according to each described eigenwert and time point;
Similarity detection module, for described very first time sequence and the second time series are contrasted, obtain the similarity of sound signal to be evaluated and described reference audio signal according to comparing result, wherein said second time series is the time series of reference audio signal corresponding to the sound signal described to be evaluated that obtains in advance.
5. audio similarity pick-up unit according to claim 4, is characterized in that, described similarity detection module comprises:
Matching unit, for the order according to the eigenwert in very first time sequence, in very first time sequence an one selected eigenwert is mated with each eigenwert in the second time series, judges in described second time series, whether there is the eigenwert of mating with described selected eigenwert;
Revise and counting unit, for when there being the eigenwert of coupling, determine the mistiming of the time point that time point corresponding to the eigenwert of described coupling is corresponding with described selected eigenwert, described selected eigenwert and each time point corresponding to the follow-up each eigenwert of described selected eigenwert are all added the described mistiming, when the described mistiming is less than predetermined threshold value, the number that eigenwert is mated is added 1, and using the next eigenwert of described selected eigenwert as new described selected eigenwert;
Eigenwert selectes unit, for when not having the eigenwert of mating, using the next eigenwert of the described selected eigenwert in very first time sequence as new described selected eigenwert;
Similarity detecting unit, for after each selected eigenwert in very first time sequence has been mated with each eigenwert in the second time series, according to the number that the eigenwert in very first time sequence is mated with the eigenwert in the second time series, obtain the similarity of sound signal to be evaluated and reference audio signal.
6. the audio similarity pick-up unit according to claim 4 or 5, is characterized in that, described audio signal frequency spectrum determination module comprises:
Go interference units, for going interference to described sound signal to be evaluated;
Audio signal frequency spectrum determining unit, for going the sound signal to be evaluated after disturbing to carry out framing, pre-emphasis, add the bright window of Hamming and Fourier transform, obtains audio signal frequency spectrum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510148926.XA CN104810025B (en) | 2015-03-31 | 2015-03-31 | Audio similarity detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510148926.XA CN104810025B (en) | 2015-03-31 | 2015-03-31 | Audio similarity detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104810025A true CN104810025A (en) | 2015-07-29 |
| CN104810025B CN104810025B (en) | 2018-04-20 |
Family
ID=53694812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510148926.XA Active CN104810025B (en) | 2015-03-31 | 2015-03-31 | Audio similarity detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104810025B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105897360A (en) * | 2016-05-18 | 2016-08-24 | 国家新闻出版广电总局监管中心 | Method and system for judging broadcast quality and effect |
| CN106100771A (en) * | 2016-06-16 | 2016-11-09 | 苏州科达科技股份有限公司 | A kind of two-way time delay detecting method and device |
| CN106294567A (en) * | 2016-07-26 | 2017-01-04 | 腾讯科技（深圳）有限公司 | A kind of Audio Sorting method and apparatus |
| CN106681997A (en) * | 2015-11-05 | 2017-05-17 | 中国移动通信集团公司 | Information processing method and device |
| CN106935248A (en) * | 2017-02-14 | 2017-07-07 | 广州孩教圈信息科技股份有限公司 | A kind of voice similarity detection method and device |
| CN107257338A (en) * | 2017-06-16 | 2017-10-17 | 腾讯科技（深圳）有限公司 | media data processing method, device and storage medium |
| CN107481738A (en) * | 2017-06-27 | 2017-12-15 | 中央电视台 | Real-time audio comparison method and device |
| CN108877841A (en) * | 2018-06-06 | 2018-11-23 | 姜涵予 | A kind of method and device for evaluating and testing Language State |
| CN109087669A (en) * | 2018-10-23 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Audio similarity detection method, device, storage medium and computer equipment |
| CN109658941A (en) * | 2018-12-03 | 2019-04-19 | 四川虹美智能科技有限公司 | A kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition |
| CN110491413A (en) * | 2019-08-21 | 2019-11-22 | 中国传媒大学 | A kind of audio content consistency monitoring method and system based on twin network |
| CN110718237A (en) * | 2018-07-12 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Crosstalk data detection method and electronic device |
| CN111489764A (en) * | 2020-03-30 | 2020-08-04 | 北京讯听网络技术有限公司 | Method and device for matching audio features and positioning start time of audio program |
| CN112534800A (en) * | 2018-07-18 | 2021-03-19 | 谷歌有限责任公司 | Echo detection |
| CN112786015A (en) * | 2019-11-06 | 2021-05-11 | 阿里巴巴集团控股有限公司 | Data processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101430876A (en) * | 2007-11-08 | 2009-05-13 | 中国科学院声学研究所 | Singing marking system and method |
| CN101471068A (en) * | 2007-12-26 | 2009-07-01 | 三星电子株式会社 | Method and system for searching music files based on wave shape through humming music rhythm |
| CN101894552A (en) * | 2010-07-16 | 2010-11-24 | 安徽科大讯飞信息科技股份有限公司 | Speech spectrum segmentation based singing evaluating system |
| CN102110435A (en) * | 2009-12-23 | 2011-06-29 | 康佳集团股份有限公司 | Method and system for karaoke scoring |
| CN103165119A (en) * | 2013-01-31 | 2013-06-19 | 华为技术有限公司 | Method and system for singing through karaok television (KTV) |
| WO2013157254A1 (en) * | 2012-04-18 | 2013-10-24 | Sony Corporation | Sound detecting apparatus, sound detecting method, sound feature value detecting apparatus, sound feature value detecting method, sound section detecting apparatus, sound section detecting method, and program |
| CN104064180A (en) * | 2014-06-06 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Singing scoring method and device |
-
2015
- 2015-03-31 CN CN201510148926.XA patent/CN104810025B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101430876A (en) * | 2007-11-08 | 2009-05-13 | 中国科学院声学研究所 | Singing marking system and method |
| CN101471068A (en) * | 2007-12-26 | 2009-07-01 | 三星电子株式会社 | Method and system for searching music files based on wave shape through humming music rhythm |
| CN102110435A (en) * | 2009-12-23 | 2011-06-29 | 康佳集团股份有限公司 | Method and system for karaoke scoring |
| CN101894552A (en) * | 2010-07-16 | 2010-11-24 | 安徽科大讯飞信息科技股份有限公司 | Speech spectrum segmentation based singing evaluating system |
| WO2013157254A1 (en) * | 2012-04-18 | 2013-10-24 | Sony Corporation | Sound detecting apparatus, sound detecting method, sound feature value detecting apparatus, sound feature value detecting method, sound section detecting apparatus, sound section detecting method, and program |
| CN103165119A (en) * | 2013-01-31 | 2013-06-19 | 华为技术有限公司 | Method and system for singing through karaok television (KTV) |
| CN104064180A (en) * | 2014-06-06 | 2014-09-24 | 百度在线网络技术（北京）有限公司 | Singing scoring method and device |
Non-Patent Citations (1)
| Title |
|---|
| 高彦: ""基于相似度的音频检索系统的设计与实现"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106681997A (en) * | 2015-11-05 | 2017-05-17 | 中国移动通信集团公司 | Information processing method and device |
| CN106681997B (en) * | 2015-11-05 | 2020-09-08 | 中国移动通信集团公司 | Information processing method and device |
| CN105897360B (en) * | 2016-05-18 | 2018-12-11 | 国家新闻出版广电总局监管中心 | A kind of broadcasting-quality and effect method of discrimination and system |
| CN105897360A (en) * | 2016-05-18 | 2016-08-24 | 国家新闻出版广电总局监管中心 | Method and system for judging broadcast quality and effect |
| CN106100771A (en) * | 2016-06-16 | 2016-11-09 | 苏州科达科技股份有限公司 | A kind of two-way time delay detecting method and device |
| CN106100771B (en) * | 2016-06-16 | 2018-07-03 | 苏州科达科技股份有限公司 | A kind of two-way time delay detecting method and device |
| CN106294567A (en) * | 2016-07-26 | 2017-01-04 | 腾讯科技（深圳）有限公司 | A kind of Audio Sorting method and apparatus |
| CN106935248A (en) * | 2017-02-14 | 2017-07-07 | 广州孩教圈信息科技股份有限公司 | A kind of voice similarity detection method and device |
| CN106935248B (en) * | 2017-02-14 | 2021-02-05 | 广州孩教圈信息科技股份有限公司 | Voice similarity detection method and device |
| CN107257338A (en) * | 2017-06-16 | 2017-10-17 | 腾讯科技（深圳）有限公司 | media data processing method, device and storage medium |
| CN107257338B (en) * | 2017-06-16 | 2018-09-28 | 腾讯科技（深圳）有限公司 | media data processing method, device and storage medium |
| CN107481738A (en) * | 2017-06-27 | 2017-12-15 | 中央电视台 | Real-time audio comparison method and device |
| CN107481738B (en) * | 2017-06-27 | 2021-06-08 | 中央电视台 | Real-time audio comparison method and device |
| CN108877841A (en) * | 2018-06-06 | 2018-11-23 | 姜涵予 | A kind of method and device for evaluating and testing Language State |
| CN110718237A (en) * | 2018-07-12 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Crosstalk data detection method and electronic device |
| CN110718237B (en) * | 2018-07-12 | 2023-08-18 | 阿里巴巴集团控股有限公司 | Crosstalk data detection method and electronic equipment |
| CN113724724B (en) * | 2018-07-18 | 2023-10-20 | 谷歌有限责任公司 | Echo detection |
| CN113724724A (en) * | 2018-07-18 | 2021-11-30 | 谷歌有限责任公司 | Echo detection |
| CN112534800A (en) * | 2018-07-18 | 2021-03-19 | 谷歌有限责任公司 | Echo detection |
| CN109087669A (en) * | 2018-10-23 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Audio similarity detection method, device, storage medium and computer equipment |
| CN109658941A (en) * | 2018-12-03 | 2019-04-19 | 四川虹美智能科技有限公司 | A kind of intelligent refrigerator information flow method for pushing and device based on Application on Voiceprint Recognition |
| CN109658941B (en) * | 2018-12-03 | 2021-02-19 | 四川虹美智能科技有限公司 | Intelligent refrigerator information flow pushing method and device based on voiceprint recognition |
| CN110491413A (en) * | 2019-08-21 | 2019-11-22 | 中国传媒大学 | A kind of audio content consistency monitoring method and system based on twin network |
| CN112786015A (en) * | 2019-11-06 | 2021-05-11 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN111489764A (en) * | 2020-03-30 | 2020-08-04 | 北京讯听网络技术有限公司 | Method and device for matching audio features and positioning start time of audio program |
| CN111489764B (en) * | 2020-03-30 | 2023-09-22 | 北京讯听网络技术有限公司 | Method and device for matching audio features and positioning audio program starting time |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104810025B (en) | 2018-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104810025A (en) | Audio similarity detecting method and device | |
| CN1957396B (en) | Device and method for analyzing an information signal | |
| CN102956230B (en) | The method and apparatus that song detection is carried out to audio signal | |
| CN106611604B (en) | Automatic voice superposition detection method based on deep neural network | |
| CN103440873B (en) | A kind of music recommend method based on similarity | |
| CN107133135B (en) | Keyboard key detection method based on statistics and sound positioning | |
| CN110880329A (en) | Audio identification method and equipment and storage medium | |
| CN108831506A (en) | Digital audio based on GMM-BIC distorts point detecting method and system | |
| CN104221079A (en) | Modified Mel filter bank structure using spectral characteristics for sound analysis | |
| CN105280196A (en) | Method and system for detecting chorus | |
| CN108538312A (en) | Digital audio based on bayesian information criterion distorts a method for automatic positioning | |
| Morrison | Vowel inherent spectral change in forensic voice comparison | |
| CN109841219A (en) | Replay Attack method is cheated using speech amplitude information and a variety of phase-detection voices | |
| CN107274912B (en) | Method for identifying equipment source of mobile phone recording | |
| CN109997186A (en) | A kind of device and method for acoustic environment of classifying | |
| CN109817223A (en) | Phoneme notation method and device based on audio-frequency fingerprint | |
| CN106128464B (en) | UBM divides the method for building up of word model, vocal print feature generation method and device | |
| CN110324657A (en) | Model generation, method for processing video frequency, device, electronic equipment and storage medium | |
| CN105654964A (en) | Recording audio device source determination method and device | |
| WO2022142755A1 (en) | Calculation method and device for interval transit time, and storage medium | |
| CN114333844A (en) | Voiceprint recognition method, voiceprint recognition device, voiceprint recognition medium and voiceprint recognition equipment | |
| US9183840B2 (en) | Apparatus and method for measuring quality of audio | |
| Prapcoyo et al. | Implementation of Mel Frequency Cepstral Coefficient and Dynamic Time Warping For Bird Sound Classification | |
| CN115148208B (en) | Audio data processing method and device, chip and electronic equipment | |
| CN113782051B (en) | Broadcast effect classification method and system, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zeng Rong Inventor after: Zhu Yingbo Inventor after: Wu Weifen Inventor after: Shi Yipeng Inventor after: Pan Zhifeng Inventor before: Zeng Rong Inventor before: Wu Weifen |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |