G. Tzanetakis and P. Cook. A framework for audio analysis based on classification and temporal segmentation. In Proc.25th Euromicro Conference. Workshop on Music Technology and Audio Processing, 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Speech/Music Discriminator Based on RMS and Zero-Crossings - Panagiotakis, Tziritas (2004) (2 citations) (Correct)
....of 98 is reported. Scheirer and Slaney [5] used thirteen features, of whicheight are extracted from the power spectrum density, for classifying audio segments. A correct classification percentage of 94.2 is reported for 20 msec segments and 98.6 for 2.4 sec segments. Tzanetakis and Cook [8] proposed a general framework for integrating, experimenting and evaluating different techniques of audio segmentation and classification. In addition they proposed a segmentation method based on feature change detection. For their experiments on a large data set a classifier performance of about ....
....of the signal is more clear in music than in speech. This is due to the fact that speechcontains frequent short pauses, where both the RMS and ZC are close to zero, and therefore correlated in this case. We exploit this possible discrimination in a feature defined for the classification. In [5] [8] and [9] the classification uses features extracted from the power spectrum density computed by the FFT as the spectral centroid, whichhowever is strongly correlated with the zero crossing rate. The maximal frequency and the pitchhave been also used, as well as the power spectrum ....
G. Tzanetakis and P. Cook. A framework for audio analysis based on classification and temporal segmentation. In Proc.25th Euromicro Conference. Workshop on Music Technology and Audio Processing, 1999.
MARSYAS: A framework for audio analysis - Tzanetakis, Cook (2000) (14 citations) Self-citation (Tzanetakis Cook) (Correct)
....addition, the user can combine time regions to form a time tree that can be used for multi resolution browsing and annotation. The tree captures the hierarchical nature of music pieces, and therefore can be used for musical analysis. 5 Applications The initial description of MARSYAS appeared in [Tzanetakis and Cook, 1999a] A more detailed description of the segmentation algorithm as well as some user experiments performed for evaluation are given in [Tzanetakis and Cook, 1999b] A number of di#erent applications have been developed using our system. Most of them are undergraduate senior theses and class ....
Tzanetakis, G. and Cook, P. (1999a). A framework for audio analysis based on classification and temporal segmentation. In Proc.25th Euromicro Conference. Workshop on Music Technology and Audio Processing, Milan, Italy. IEEE Computer Society.
Sound Analysis Using Mpeg Compressed Audio - Tzanetakis, Cook (2000) (1 citation) Self-citation (Tzanetakis Cook) (Correct)
....the feature calculation an MP3 decoder was implemented in C . The source code is loosely based on the Fraunhaufer institute reference software implementation and other open source implementations. The feature calculation, classification and segmentation componenents were integrated using MARSYAS [10] an object oriented framework for building audio analysis tools written in C and JAVA. The combined decoding and classification segmentation runs real time on a Pentium II PC. The source code for the feature calculation is available upon request. 8. FUTURE WORK For statistical pattern ....
G. Tzanetakis and P. Cook, "A framework for audio analysis based on classification and temporal segmentation, " in Proc.25th Euromicro Conference. Workshop on Music Technology and Audio Processing, Milan, Italy, 1999, IEEE Computer Society.
Experiments in Computer-Assisted Annotation of Audio - George Tzanetakis Computer (2000) Self-citation (Tzanetakis Cook) (Correct)
....can then be edited by adding deleting boundaries until the desired segmentation is reached. Finally, the plug in architecture of the system easily allows the use of segmentation results from other analysis tools such as a speech recognition system. The system has been implemented using MARSYAS [8] an object oriented framework for building audio analysis applications. A client server architecture is used. The graphical user interface (written in JAVA) acts as a client to the server engine (written in C ) where all the signal processing is done. The system runs on Solaris, SGI, Linux and ....
G. Tzanetakis and P. Cook, "A framework for audio analysis based on classification and temporal segmentation," in Proc.25th Euromicro Conference. Workshop on Music Technology and Audio Processing, Milan, Italy, 1999, IEEE Computer Society.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC