Automatic Classification of Music Signals

Heittola, Toni

Collections of digital music have become increasingly common over the recent years. As the amount of data increases, digital content management is becoming more important. In this thesis, we are studying content-based classification of acoustic musical signals according to their musical genre (e.g., classical, rock) and the instruments used. A listening experiment is conducted to study human abilities to recognise musical genres. This thesis covers a literature review on human musical genre recognition, state-of-the-art musical genre recognition systems, and related fields of research. In addition, a general-purpose music database consisting of recordings and their manual annotations is introduced. The theory behind the used features and classifiers is reviewed and the results from the simulations are presented. The developed musical genre recognition system uses mel-frequency cepstral coefficients to represent the time-varying magnitude spectrum of a music signal. The class-conditional feature densities are modelled with hidden Markov models. Musical instrument detection for a few pitched instruments from music signals is also studied using the same structure. Furthermore, this thesis proposes a method for the detection of drum instruments. The presence of drums is determined based on the periodicity of the amplitude envelopes of the signal at subbands. The conducted listening experiment shows that the recognition of musical genres is not a trivial task even for humans. On the average, humans are able to recognise the correct genre in 75 % of cases (given five-second samples). Results also indicate that humans can do rather accurate musical genre recognition without long-term temporal features, such as rhythm. For the developed automatic recognition system, the obtained recognition accuracy for six musical genres was around 60 %, which is comparable to the state-of-the-art systems. Detection accuracy of 81 % was obtained with the proposed drum instrument detection method.


Musical genre classification

Research areas