In large MP3 databases, files are typically generated with different parameter settings, i.e., bit rate and sampling rates. This is of concern for MIR applications, as encoding difference can potentially confound meta-data estimation and similarity evaluation. In this paper we will discuss the influence of MP3 coding for the Mel frequency cepstral coeficients (MFCCs). The main result is that the widely used subset of the MFCCs is robust at bit rates equal or higher than 128 kbits/s, for the implementations we have investigated. However, for lower bit rates, e.g., 64 kbits/s, the implementation of the Mel filter bank becomes an issue.
|Title of host publication||Proceedings of the Seventh International Conference on Music Information Retrieval (ISMIR)|
|Publication status||Published - 2006|
|Event||Seventh International Conference on Music Information Retrieval (ISMIR) - |
Duration: 1 Jan 2006 → …
|Conference||Seventh International Conference on Music Information Retrieval (ISMIR)|
|Period||01/01/2006 → …|
- Mel frequency cepstral coefficients