On Musical Performances Identification, Entropy and String Matching

Camarena-Ibarrola, Antonio; Chávez, Edgar

doi:10.1007/11925231_91

Cited by 12 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted experiments in which we can identify a song with pieces of only 1-s using the described in [3], the feature extracted from the audio signal is multi-band spectral entropy, not only recognized the song but the precise spot where the piece of a second is located within the song, although this piece has a high noise level. This is just what we need to characterize a musical performance for monitoring purposes which is the first part of our method.…”

Section: Our Proposalmentioning

confidence: 99%

See 1 more Smart Citation

Online music tracking with global alignment

Camarena-Ibarrola

Chávez

2011

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

To make audio monitoring, the state of the art in this area makes use of local alignment algorithms between the objective audio and musical interpretation.The inductive hypothesis of a local alignment tool is that the alignment is correct to the current position of an error this is drag and accumulate to subsequent errors which do not recover unless elaborate heuristics are used. Our approach uses a local non-alignment scheme based on the audio search the entire purpose of short segments of audio taken from musical performance to get the k nearest audio segments (the proximity is determined using audio tracks based on entropy signs).The current audio segment of the play is paired with the nearest (in time) between the k previously selected audio segments of the target audio.To our knowledge, this is the first algorithm able to start up from an arbitrary point in the audio end, for example, if the musical performance had already begun when the monitoring system just went on.We complemented the overall strategy through a simple heuristic of ignoring the candidates when they are all too far in time with respect to the last position reported by the system.We have tested our method with 62 musical pieces, some of which are pop and classical music mostly.For every song we have two interpretations, we use one as the audio object and the other as the interpretation which will be monitored.We obtained excellent results.Keywords Follow-up Á Music Á Entropy Á Index Á Near GroundsReal-time tracking of musical performances consists in setting the position on the target audio segment most recently captured audio of a musical performance as this is being played. Now explain briefly three applications of real-time tracking of musical performances: (a) The virtual music teacher, (b) auto-accompaniment of soloists, and (c) automatically added special effects in live performance. For the virtual master of music, the sound objective is wellexecuted piece of music by a professional musician. Musical performance which will be followed is that produced by the student. A music teacher teaches only one student at a time, as the student plays his instrument, the teacher makes comments pointing out errors or endorse the interpretation. A virtual teacher should do the same, use the audio signal generated by the student, and processed in real time and provide appropriate instructions to the student. The advantage of a virtual teacher that can generate many instances of the same and therefore simultaneously serve many students. For the automatic accompaniment of a singer or a solo audio music performance, the target audio would be made possibly in a recording studio, while the music that will be followed up is the live performance of the musician or singer. The system plays music accompaniment while generating activities (e.g., introducing delays in background music), these systems are true An earlier version of this work was presented at

show abstract

Section: Our Proposalmentioning

confidence: 99%

“…In [3], the removal of a very robust audio fingerprint based on the evolution over time of entropy spectral frequency bands was used for the purpose of music retrieval by content. The same audio track was successfully used for automatic monitoring of radio stations in [4] with excellent results.…”

Section: Multi-band Spectral Entropy Signaturementioning

confidence: 99%

Online music tracking with global alignment

Camarena-Ibarrola

Chávez

2011

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several features have been used for audio-fingerprinting purposes, among them, the Mel-frequency Cepstral coefficients (MFCC) [3], [4]; the Spectral Flatness Measure (SFM) [5]; tonality [6] and chroma values [7], most of them are analyzed in depth in [8]. Recently in [9,10] the use of entropy as the sole feature for audio fingerprinting proved to be much more robust to severe degradations outperforming previous approaches. This technique is the Multi-Band Spectral Entropy Signature or MBSES described in some detail in this paper.…”

Section: Related Workmentioning

confidence: 99%

“…With this approach, called Time-domain Entropy Signature (TES) the recall was high; but with some degradations, as equalization, it dropped quickly. To solve this problem in [9] the signal was divided in bands according to the Bark scale in the frequency domain, then entropy is determined for each band. The result was a very strong signature, with perfect recall even for strong degradations.…”

Section: The Multi Band Spectral Entropy Signaturementioning

confidence: 99%

Robust Radio Broadcast Monitoring Using a Multi-Band Spectral Entropy Signature

Camarena-Ibarrola¹,

Chávez²,

Téllez³

2009

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. Monitoring media broadcast content has deserved a lot of attention lately from both academy and industry due to the technical challenge involved and its economic importance (e.g. in advertising). The problem pose a unique challenge from the pattern recognition point of view because a very high recognition rate is needed under non ideal conditions. The problem consist in comparing a small audio sequence (the commercial ad) with a large audio stream (the broadcast) searching for matches.In this paper we present a solution with the Multi-Band Spectral Entropy Signature (MBSES) which is very robust to degradations commonly found on amplitude modulated (AM) radio. Using the MBSES we obtained perfect recall (all audio ads occurrences were accurately found with no false positives) in 95 hours of audio from five different am radio broadcasts. Our system is able to scan one hour of audio in 40 seconds if the audio is already fingerprinted (e.g. with a separated slave computer), and it totaled five minutes per hour including the fingerprint extraction using a single core off the shelf desktop computer with no parallelization.

show abstract