WO2014098498A1 - Appareil de correction auditive et procédé de correction auditive pour celui-ci - Google Patents

Appareil de correction auditive et procédé de correction auditive pour celui-ci Download PDF

Info

Publication number
WO2014098498A1
WO2014098498A1 PCT/KR2013/011883 KR2013011883W WO2014098498A1 WO 2014098498 A1 WO2014098498 A1 WO 2014098498A1 KR 2013011883 W KR2013011883 W KR 2013011883W WO 2014098498 A1 WO2014098498 A1 WO 2014098498A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio data
onset
information
pitch
audio
Prior art date
Application number
PCT/KR2013/011883
Other languages
English (en)
Korean (ko)
Other versions
WO2014098498A8 (fr
Inventor
전상배
이교구
성두용
허훈
김선민
김정수
손상모
Original Assignee
삼성전자 주식회사
서울대학교산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from KR1020130157926A external-priority patent/KR102212225B1/ko
Application filed by 삼성전자 주식회사, 서울대학교산학협력단 filed Critical 삼성전자 주식회사
Priority to CN201380067507.2A priority Critical patent/CN104885153A/zh
Priority to US14/654,356 priority patent/US9646625B2/en
Publication of WO2014098498A1 publication Critical patent/WO2014098498A1/fr
Publication of WO2014098498A8 publication Critical patent/WO2014098498A8/fr

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/90—Pitch determination of speech signals

Definitions

  • the present invention relates to an audio calibrating apparatus and an audio calibrating method thereof, and more particularly, an audio calibrating apparatus for detecting onset information and pitch information of audio data and correcting the same according to the onset information and pitch information of reference audio data, and audio correction thereof. It is about a method.
  • the playing sound that occurs when a person sings or plays a stringed instrument includes a soft-onset in which each note is connected to each other. That is, in the case of playing sound that occurs when a person sings or plays a stringed instrument, when only the pitch is corrected without searching for the onset of each note, the pitch is lost in the middle, or the pitch is corrected at the wrong note. Points may occur.
  • the present invention has been made to solve the above-described problem, and an object of the present invention is to detect an onset and a pitch of audio data and to correct the onset and pitch of reference audio data, and an audio correction apparatus and its audio correction method. In providing.
  • an audio correction method comprises the steps of: receiving audio data; Analyzing on the harmonic component of the audio data to detect onset information; Detecting pitch information of the audio data based on the detected onset information; Sorting the audio data with reference audio data based on the detected onset information and the pitch information; And correcting the audio data aligned with the reference audio data to match the reference audio data.
  • the onset information may be detected by performing a cepstral analysis on the audio data, and analyzing a harmonic component of the capstrated analysis audio data.
  • the detecting of the onset information may include: performing a cepstral analysis on the audio data; Selecting the harmonic component of the current frame using the pitch component of the previous frame; Calculating a cepstral coefficient for a plurality of harmonic components using the harmonic component of the current frame and the harmonic component of the previous frame; Generating a detection function by summing capstratum coefficients for the plurality of harmonic components; Extracting an onset candidate group by detecting a peak of the detection function; And detecting onset information by removing a plurality of adjacent onsets among the onset candidate groups.
  • the cap stratum coefficient when the harmonic component of the previous frame is present, the cap stratum coefficient is high, and when the harmonic component of the previous frame is not present, the cap stratum coefficient may be low.
  • pitch information between the detected onset components may be detected using a correntropy pitch detection method.
  • the sorting may be performed by comparing the audio data with reference audio data using a dynamic time warping technique.
  • the aligning may include calculating an onset correction ratio and a pitch correction ratio of the audio data with respect to the reference audio data.
  • the correcting may include correcting the audio data according to the calculated onset correction ratio and the pitch correction ratio.
  • the audio data may be corrected by preserving a formant of the audio data using an SOLA algorithm.
  • the audio correction device the input unit for receiving audio data; Onset detection unit for detecting information onset (onse t) by analyzing the harmonic component of the audio data; A pitch detector for detecting pitch information of the audio data based on the detected onset information; The audio data is referenced audio based on the detected onset information and the pitch information.
  • An alignment unit to arrange the data in comparison with the data; And a correction unit configured to correct audio data aligned with the reference audio data to match the reference audio data.
  • the onset detector may detect the onset information by performing a cepstral analysis on the audio data and by analyzing a harmonic component of the capstrated analysis audio data.
  • the onset detection unit the capstrum for the audio data
  • a capstrum analyzer for performing cepstral analysis;
  • a selection unit for selecting the harmonic component of the current frame using the pitch component of the previous frame;
  • a coefficient calculator configured to calculate a capstral coefficient for a plurality of harmonic components using the harmonic component of the current frame and the harmonic component of the previous frame;
  • a function generator for generating a detection function by summing capstrum coefficients of the plurality of harmonic components;
  • An onset candidate group extraction unit for extracting an onset candidate group by detecting a peak of the detection function;
  • an onset information detector for detecting onset information by removing a plurality of adjacent onsets among the onset candidate groups.
  • the coefficient calculating unit may display a high capstratum coefficient when the harmonic component of the previous frame is present, and may display a low capstratum coefficient when the harmonic component of the previous frame is not present.
  • the pitch detector may detect pitch information between onset components detected using a correntropy pitch detection method.
  • the sorting unit may align the audio data with reference audio data by using a dynamic time warping technique.
  • the alignment unit may calculate an onset correction ratio and a pitch correction ratio of the audio data with respect to the reference audio data.
  • the correction unit may correct the audio data according to the calculated onset correction ratio and the pitch correction ratio.
  • the correction unit may correct the audio data by preserving the components of the audio data using an SOLA algorithm.
  • the onset detection method of the audio correction apparatus performing a cepstral analysis (audio) on the audio data; Selecting the harmonic component of the current frame using the pitch component of the previous frame; The harmonic component of the current frame and the previous frame Calculating a cepstral coefficient for the plurality of harmonic components using the arbitrary harmonic components; Generating a detection function by summing capstratum coefficients for the plurality of harmonic components; Extracting an onset candidate group by detecting a peak of the detection function; And detecting onset information by removing a plurality of adjacent onsets among the onset candidate groups.
  • audio cepstral analysis
  • onset detection is possible even in audio data in which the onset is not clearly distinguished, such as a song sung or a performance of a stringed instrument, thereby enabling more accurate audio correction.
  • FIG. 1 is a flowchart illustrating an audio correction method according to an embodiment of the present invention
  • FIG. 2 is a flowchart illustrating a method for detecting onset information according to an embodiment of the present invention
  • 3A to 3D are graphs showing audio data generated while detecting onset information according to an embodiment of the present invention.
  • FIG. 4 is a flowchart illustrating a pitch information detection method according to an embodiment of the present invention.
  • 5A and 5B are graphs for describing a method of detecting a current of curvature according to an embodiment of the present invention.
  • 6a to 6d are views for explaining a dynamic time matching method according to an embodiment of the present invention.
  • FIG. 7 is a view for explaining a time stretching correction method of audio data according to an embodiment of the present invention.
  • FIG. 8 is a block diagram briefly illustrating a configuration of an audio correction apparatus according to an embodiment of the present invention.
  • FIG. 1 is a flowchart illustrating an audio correction method of an audio correction apparatus 800 according to an embodiment of the present invention.
  • the audio calibrating apparatus 800 receives audio data (S110).
  • the audio data includes data including a song sung by a person or a performance sound played by a musical instrument. Can be.
  • the audio compensator 800 analyzes the harmonic component to obtain onset information.
  • onset included in a song sung by a person may mean a point at which vowels start.
  • the audio correction device 800 is a capstrum for audio data
  • Onset information may be detected by using a HCROkrmonic Cepstrum Regularity (CEROkrmonic Cepstrum Regularity) method, which performs a cepstral analysis and analyzes the harmonic components of the capstrum analyzed audio data.
  • CEROkrmonic Cepstrum Regularity CEROkrmonic Cepstrum Regularity
  • a method of detecting the silver set information by analyzing the harmonic component by the audio calibrating apparatus 800 will be described in detail with reference to FIG. 2.
  • the audio calibrating apparatus 800 performs a capstral analyst on the input audio data (S121).
  • the audio calibrating apparatus 800 may perform a preprocessing process such as pre-emphasis on the input audio data.
  • the audio correction apparatus 800 performs a fast Fourier transform (FFT) on the input audio data.
  • the audio calibrating apparatus 800 may log the converted audio data and perform a discrete cosine transform (DCT) on the logged audio data to perform capstram analysis.
  • FFT fast Fourier transform
  • DCT discrete cosine transform
  • the audio compensator 800 then extracts the harmonic component of the current frame.
  • the audio calibrating apparatus 800 may detect the pitch information of the previous frame and select the harmonic frequency of the harmonic component of the current frame by using the detected pitch information of the previous frame.
  • the audio correction apparatus 800 calculates a capstral coefficient for the plurality of harmonic components using the harmonic component of the current frame and the previous frame harmonic component (S123). In this case, when there is a harmonic component of the previous frame, the audio compensator 800 calculates a high capstratum coefficient, and when there is no harmonic component of the previous frame, the audio compensator 800 determines the capstrum coefficient. Can be calculated low.
  • the audio calibrating apparatus 800 generates a detection function by summing capstrum coefficients of the plurality of harmonic components.
  • audio The correction device 800 receives audio data including a voice signal as shown in FIG. 3A.
  • the audio calibrating apparatus 800 may detect the plurality of harmonic wave numbers as shown in FIG. 3B through the capstrum analysis.
  • the audio calibrating apparatus 800 may calculate the cap stratum coefficients of the plurality of harmonic components as shown in FIG. 3C based on the harmonic wave frequency as shown in FIG. 3B.
  • a cap ion coefficient of the plurality of harmonic components illustrated in FIG. 3C may be added to generate a detection ion function as illustrated in FIG. 3D.
  • the audio calibrating apparatus 800 detects a peak of the generated detection function and extracts an onset candidate group. Specifically, when the harmonic component is present and other harmonic components appear, that is, at the point where the onset occurs, the cap stratum coefficient changes abruptly. Accordingly, the audio calibrating apparatus 800 may extract a peak point, which is a sharply changed point of the detection function, which is the sum of the capstrum of the plurality of harmonic components. At this time, the extracted peak point may be set as an onset candidate group.
  • the audio correction apparatus 800 detects onset information among the onset candidate groups (S126).
  • a plurality of onset candidate groups may be extracted in an adjacent section in the onset candidate groups extracted in step S125.
  • the assistants are onsets that can occur when a human voice is trembling or other noise comes in. Accordingly, the audio calibrating apparatus 800 may remove the remaining portions except one of the plurality of onset candidate groups in adjacent sections, and detect only one onset candidate group on-set information.
  • Table 1 shows the results of detecting the onset using the HCR method.
  • the F-measures of various sources are calculated from 0.60 to 0.79. have.
  • the F-measure detected by various conventional algorithms is 0.19 to 0.56, more accurate onset detection may be possible by detecting onset using the HCR method as the present invention.
  • the audio calibrating apparatus 800 detects pitch information based on the detected onset information (S130). In particular, the audio correction device 800
  • Pitch information between detected onset components may be detected using a correntropy pitch detection method.
  • An embodiment in which the audio calibrating apparatus 800 detects pitch information between onset components by using a current tracking pitch detection method will be described with reference to FIG. 4.
  • the audio calibrating apparatus 800 divides a signal between onsets (S131).
  • the audio calibrating apparatus 800 may divide a signal between the plurality of onsets based on the onsets detected in operation S120.
  • the audio calibrating apparatus 800 performs gammatone filtering on the input signal.
  • the audio calibrating apparatus 800 applies 64 gamma tone filters to the input signal.
  • the plurality of gamma tone filters are divided in frequency according to bandwidth.
  • the center frequency of the filter is divided into equal intervals, the bandwidth can be set between 80Hz and 4000Hz.
  • the audio correction apparatus 800 In operation S133, the audio correction apparatus 800 generates a current law for the input signal. In general, in the case of the current curriculum, a higher statistic can be obtained than the conventional aut correlation. Therefore, when dealing with human voice, frequency resolution is higher than conventional auto-correlation. Meanwhile, the audio calibrating apparatus 800 may obtain a current corrector function as shown in Equation 1 below.
  • V (t, s) E [(x (t ⁇ x (s)]
  • k (*, *) may be a kernel function having positive values and symmetrical characteristics.
  • the kernel function may use a Gaussian kernel. Equation of the Gaussian kernel and the current currotropy function by substituting the Gaussian kernel may be as shown in Equation 2 and Equation 3 below. ⁇ Equation 2>
  • the audio calibrating apparatus 800 then picks up the peak of the current law.
  • the audio compensator 800 may detect peaks having a higher frequency resolution than auto-correlation and sharper frequencies than the corresponding signal with respect to the input audio data. In this case, the audio calibrating apparatus 800 may measure a frequency of a predetermined threshold value among the calculated peaks as the pitch of the input voice signal. More specifically, FIG. 5A illustrates the normalized current law. At this time, when detecting the currotropy of 70 frames, as shown in FIG. 5B. In this case, a frequency value between the two peaks detected in FIG. 5B may mean a pitch of the corresponding frame.
  • the audio correction device 800 detects the pitch sequence on the basis of the detected pitch (S135).
  • the audio calibrating apparatus 800 may detect pitch information for a plurality of onsets and detect a detected pitch sequence for each onset.
  • the pitch is detected by using the current currotropy pitch detection method.
  • this is only an example and another method (for example,
  • auto-correlation method may be used to detect the pitch of audio data.
  • the audio calibrating apparatus 800 aligns the audio data with the reference audio data (S140).
  • the reference audio data may be audio data to be corrected by the input audio data.
  • the audio calibrating apparatus 800 may match audio data and reference audio data by using a dynamic time warping (DTW) method.
  • DTW dynamic time warping
  • the dynamic time matching method is an algorithm that finds the optimal and warping path by comparing the similarities between two sequences.
  • the audio calibrating apparatus 800 may detect a sequence X for audio data input through steps S120 and S130. A sequence Y for the reference audio data can be obtained. In addition, the audio calibrating apparatus 800 may calculate a cost matrix as shown in FIG. 6B by comparing the similarities between the sequence X and the sequence Y. FIG.
  • the audio calibrating apparatus 800 detects an optimal path for pitch information such as a dotted line shown in FIG. 6C and an optimal path for onset information such as a dotted line shown in FIG. 6D. Can be.
  • the audio calibrating apparatus 800 may calculate the onset correction ratio and the pitch correction ratio of the audio data with respect to the reference audio data while calculating the optimum path.
  • the onset correction ratio may be a time stretching ratio for correcting the length of time of the input audio data
  • the pitch correction ratio may be a ratio for guaranteeing the frequency of the input audio data. .
  • the audio calibrating apparatus 800 corrects the input audio data (S150).
  • the audio correction apparatus 800 may correct the input audio data to match the reference audio data using the onset correction ratio and the pitch correction ratio calculated in step S140.
  • the audio calibrating apparatus 800 may correct onset information of audio data by using a phase vocoder.
  • the phase vocoder may correct onset information of audio data through analysis, modification, and synthesis.
  • the audio calibrating apparatus 800 may correct the pitch information of the audio data by using a phase vocoder. In this case, the audio calibrating apparatus 800 may correct the pitch information of the audio data by using the pitch change generated when the time scale is changed through resampling. Specifically, the audio calibrating apparatus 800 performs time stretching 152 on the input audio data 151 as shown in FIG. 7A. At this time, the ratio of time stretching is equal to the value obtained by dividing the analysis suction size by the synthetic suction size. The audio calibrating apparatus 800 outputs audio data 154 through the resampling 153 again. At this time, the resampling ratio is equal to the value obtained by dividing the synthetic suction size by the analysis suction size.
  • the audio correction device 800 corrects the pitch through resampling
  • the foreman In order to prevent the formant from being changed, the input audio data may be premultiplied with a matching coefficient, P, which is a predetermined value so that the formant is maintained even after resampling.
  • the matching coefficient P may be calculated by Equation 4 below.
  • a (k) is a formant envelope.
  • the audio compensator 800 may correct audio data by preserving the formant of the audio data using a synchronized overlap add (SOLA) algorithm.
  • SOLA synchronized overlap add
  • the audio calibrating apparatus 800 may remove discontinuity occurring in the time axis by performing a phase vocoder for several initial frames and then synchronizing the input audio data with the phase vocoder performed data.
  • onset detection is possible even in audio data where onset is not clearly distinguished, such as a song sung by a person or a performance of a stringed instrument, and thus more accurate audio correction can be performed.
  • the audio calibrating apparatus 800 includes an input unit 810, an onset detector 820, a pitch detector 830, an alignment unit 840, and a correction unit 850.
  • the audio calibrating apparatus 800 may be implemented with various electronic devices such as a smart phone, a smart TV, a tablet PC, and the like.
  • the input unit 810 receives audio data.
  • the audio data may be a song sung or played by a string instrument.
  • the onset detector 820 detects an onset by analyzing a harmonic component of the input audio data.
  • the onset detector 820 may perform cepstral analysis on the audio data, and detect the onset information by analyzing the harmonic components of the captured audio data.
  • the onset detection unit 820 ' first, performing a cepstrum analysis (cepstral analysis) for the audio data as described in Figure 2.
  • the onset detector 820 selects the harmonic component of the current frame using the pitch component of the previous frame, and the harmonic component of the current frame and the previous program.
  • the harmonic component of the frame is used to calculate the cepstral coefficients for the plurality of harmonic components.
  • the onset detector 820 generates a detection function by summing capstratum coefficients of the plurality of harmonic components.
  • the onset detector 820 may detect the peak of the detection function, extract the onset candidate group, and remove the plurality of adjacent onsets from the onset candidate group to detect the onset information.
  • the pitch detector 830 detects pitch information of the audio data based on the detected onset information.
  • the pitch detection unit 830 may detect pitch information between onset components using the current currotropy pitch detection method, but this is only an example and may detect the pitch information using another method.
  • the alignment unit 840 compares the audio data with the reference audio data and sorts the audio data based on the detected onset information and the pitch information.
  • the alignment unit 840 may compare the audio data with the reference audio data and arrange the audio data using a dynamic time warping technique.
  • the alignment unit 840 may calculate the silver set correction ratio and the pitch correction ratio of the audio data with respect to the reference audio data.
  • the correction unit 850 corrects the audio data aligned with the reference audio data to match the reference audio data.
  • the correction unit 850 may correct the audio data according to the calculated onset correction ratio and the pitch correction ratio.
  • the correction unit 850 may correct the audio data using the SOLA algorithm in order to prevent a change of formants that may occur during onset and pitch correction.
  • the onset detection is possible even in the audio data in which the onset is not clearly distinguished, such as a song sung or a performance of a stringed instrument, thereby enabling more accurate audio correction.
  • the audio correction device 800 is implemented as a user terminal such as a smart phone
  • the present invention can be applied to various scenarios. For example, the user may select a song that he / she would like to sing.
  • the audio calibrating apparatus 800 obtains reference MIDI data of a song selected by the user.
  • the audio calibrating apparatus 800 may display the sheet music to guide the user to sing more accurately.
  • the audio correction apparatus 800 corrects the user's song, as described with reference to FIGS. 1 to 8. And, if the listen command is input again by the user, the audio The calibrator 800 may play the corrected song. In addition, the audio correction apparatus 800 may provide an effect such as chorus / reverb to the user. In this case, after the recording is completed, the audio calibrating apparatus 800 may provide an effect such as chorus / reverb to the song of the calibrated user. When the modification is completed, the audio correction apparatus 800 may play a song or share it with others through SNS according to a user command. Meanwhile, the audio correction method of the ODA correction apparatus 800 according to the above-described various embodiments may be implemented as a program and provided to the audio correction apparatus 800. In particular, a program including a sensing method of the mobile device 100 may be stored and provided in a non-transitory computer readable medium.
  • a non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by the device, not a medium storing data for a short time such as a register, a cache, or a memory.
  • the various applications or programs described above may be stored and provided in a non-transitory readable medium such as a CD, a DVD, a hard disk, a Blu-ray disk, a USB, a memory card, or a ROM.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Electrophonic Musical Instruments (AREA)

Abstract

L'invention concerne un appareil de correction auditive et un procédé de correction auditive pour celui-ci. Le procédé de correction auditive peut : prendre, comme entrée, des données audio ; analyser les composantes harmoniques des données audio afin de détecter des informations de début de train d'onde ; détecter des informations de hauteur sonore sur la base des informations de début de train d'onde détectées ; comparer les données audio et les données audio de référence en se basant sur les informations de début de train d'onde et les informations de hauteur sonore détectées et aligner les données audio avec les données audio de référence ; et corriger les données audio alignées avec les données audio de référence de telle sorte que les données audio puissent être assorties aux données audio de référence.
PCT/KR2013/011883 2012-12-20 2013-12-19 Appareil de correction auditive et procédé de correction auditive pour celui-ci WO2014098498A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201380067507.2A CN104885153A (zh) 2012-12-20 2013-12-19 音频校正设备及其音频校正方法
US14/654,356 US9646625B2 (en) 2012-12-20 2013-12-19 Audio correction apparatus, and audio correction method thereof

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201261740160P 2012-12-20 2012-12-20
US61/740,160 2012-12-20
KR1020130157926A KR102212225B1 (ko) 2012-12-20 2013-12-18 오디오 보정 장치 및 이의 오디오 보정 방법
KR10-2013-0157926 2013-12-18

Publications (2)

Publication Number Publication Date
WO2014098498A1 true WO2014098498A1 (fr) 2014-06-26
WO2014098498A8 WO2014098498A8 (fr) 2015-06-18

Family

ID=50978729

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2013/011883 WO2014098498A1 (fr) 2012-12-20 2013-12-19 Appareil de correction auditive et procédé de correction auditive pour celui-ci

Country Status (1)

Country Link
WO (1) WO2014098498A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106157977A (zh) * 2015-04-10 2016-11-23 科大讯飞股份有限公司 一种唱歌评测方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5749073A (en) * 1996-03-15 1998-05-05 Interval Research Corporation System for automatically morphing audio information
WO2005010865A2 (fr) * 2003-07-31 2005-02-03 The Registrar, Indian Institute Of Science Procede d'extraction et de classification d'informations de musique au moyen d'informations de continuite
US20090271197A1 (en) * 2007-10-24 2009-10-29 Red Shift Company, Llc Identifying features in a portion of a signal representing speech
JP2010026512A (ja) * 2008-07-16 2010-02-04 Honda Motor Co Ltd ビートトラッキング装置、ビートトラッキング方法、記録媒体、ビートトラッキング用プログラム、及びロボット
US20110004467A1 (en) * 2009-06-30 2011-01-06 Museami, Inc. Vocal and instrumental audio effects

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5749073A (en) * 1996-03-15 1998-05-05 Interval Research Corporation System for automatically morphing audio information
WO2005010865A2 (fr) * 2003-07-31 2005-02-03 The Registrar, Indian Institute Of Science Procede d'extraction et de classification d'informations de musique au moyen d'informations de continuite
US20090271197A1 (en) * 2007-10-24 2009-10-29 Red Shift Company, Llc Identifying features in a portion of a signal representing speech
JP2010026512A (ja) * 2008-07-16 2010-02-04 Honda Motor Co Ltd ビートトラッキング装置、ビートトラッキング方法、記録媒体、ビートトラッキング用プログラム、及びロボット
US20110004467A1 (en) * 2009-06-30 2011-01-06 Museami, Inc. Vocal and instrumental audio effects

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106157977A (zh) * 2015-04-10 2016-11-23 科大讯飞股份有限公司 一种唱歌评测方法及系统
CN106157977B (zh) * 2015-04-10 2019-11-15 科大讯飞股份有限公司 一种唱歌评测方法及系统

Also Published As

Publication number Publication date
WO2014098498A8 (fr) 2015-06-18

Similar Documents

Publication Publication Date Title
KR102212225B1 (ko) 오디오 보정 장치 및 이의 오디오 보정 방법
US11657798B2 (en) Methods and apparatus to segment audio and determine audio segment similarities
US10565970B2 (en) Method and a system for decomposition of acoustic signal into sound objects, a sound object and its use
TWI480855B (zh) 聲音訊號之特徵指紋擷取與匹配
US8494668B2 (en) Sound signal processing apparatus and method
US8853516B2 (en) Audio analysis apparatus
EP2494544A1 (fr) Estimation perceptuelle de tempo adaptable en complexité
JP2004528599A (ja) オーディトリーイベントに基づく特徴付けを使ったオーディオの比較
JP5127982B2 (ja) 音楽検索装置
US20120237041A1 (en) Method And An Apparatus For Deriving Information From An Audio Track And Determining Similarity Between Audio Tracks
EP3899701B1 (fr) Mesure temporelle a haute precision d'evenements vibro-acoustiques en synchronisation avec un signal sonore sur dispositif a ecran tactile
WO2018229497A1 (fr) Procédé et système de déclenchement d'événements
JP5395399B2 (ja) 携帯端末、拍位置推定方法および拍位置推定プログラム
CN111667803B (zh) 一种音频处理方法及相关产品
CN111737515B (zh) 音频指纹提取方法、装置、计算机设备和可读存储介质
Goldstein et al. Guitar Music Transcription from Silent Video.
WO2014098498A1 (fr) Appareil de correction auditive et procédé de correction auditive pour celui-ci
Pilia et al. Time scaling detection and estimation in audio recordings
CN110751935A (zh) 乐器演奏点的确定及节奏评分的方法
Coyle et al. Onset detection using comb filters
Tang et al. Melody Extraction from Polyphonic Audio of Western Opera: A Method based on Detection of the Singer's Formant.
CN103531220A (zh) 歌词校正方法及装置
CN107452363A (zh) 乐器校音方法及系统
KR20060081500A (ko) 음악에서의 비브라토 자동 검출방법
Martin et al. Exemplar-based Assignment of Large Missing Audio Parts using String Matching on Tonal Features.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13866184

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14654356

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13866184

Country of ref document: EP

Kind code of ref document: A1