Robust audio identification for MP3 popular music

Abstract

Audio identification via fingerprint has been an active research field with wide applications for years. Many technical papers were published and commercial software systems were also employed. However, most of these previously reported methods work on the raw audio format in spite of the fact that nowadays compressed format audio, especially MP3 music, has grown into the dominant way to store on personal computers and transmit on the Internet. It would be interesting if a compressed unknown audio fragment is able to be directly recognized from the database without the fussy and time-consuming decompression-identification-recompression procedure. So far, very few algorithms run directly in the compressed domain for music information retrieval, and most of them take advantage of MDCT coefficients or derived energy type of features. As a first attempt, we propose in this paper utilizing compressed-domain spectral entropy as the audio feature to implement a novel audio fingerprinting algorithm. The compressed songs stored in a music database and the possibly distorted compressed query excerpts are first partially decompressed to obtain the MDCT coefficients as the intermediate result. Then by grouping granules into longer blocks, remapping the MDCT coefficients into 192 new frequency lines to unify the frequency distribution of long and short windows, and defining 9 new subbands which cover the main frequency bandwidth of popular songs in accordance with the scale-factor bands of short windows, we calculate the spectral entropy of all consecutive blocks and come to the final fingerprint sequence by means of magnitude relationship modeling. Experiments show that such fingerprints exhibit strong robustness against various audio signal distortions like recompression, noise interference, echo addition, equalization, band-pass filtering, pitch shifting, and slight time-scale modification etc. For 5s-long query examples which might be severely degraded, an average top-five retrieval precision rate of more than 90% can be obtained in our test data set composed of 1822 popular songs.

Data sonification of film capacitors

“…These all indicate that the sonification results are indeed accurate in transmitting information in the data of film capacitors, and this effect is reflected in all the tested data. Of course, the losses and biases that exist during the process of converting data into sound [30] are also worth the attention of researchers who are committed to improving the effectiveness of data sonification in the future.…”

Genre Classification of Traditional Malay Music Using Spectrogram Correlation

“…A long frame length resulted in the spectrogram having low time resolution, which makes the representation insensitive to time variations [15]. In addition, large overlap is an advantage when dealing with using short query music against the long original signal [16][17].…”

MP3 File Identification Based on Concurrence Order of Metadata

“…According to the recent report in [2,3], about 90% of the music contents is traded by an MP3 file type in music market whether it is online or off line. Therefore the identification of MP3 file plays important role of a music searching, a storage indexing and a tracking of illegal distributions [4].…”