We use the NNLS approximate transcription and no normalization. Concerning the parameters, we used a window size of 8192 samples and a step size of 4410 samples leading to a chromagram resolution of 10 Hz.
We use the NNLS chroma algorithm as published in, which is freely available as a VAMP plugin. In order to allow reproducibility of some of our experiments, we provide chroma features of the pieces. Since the dataset consists of commercial recordings, we cannot make the audio files publicly available. If you publish results obtained using these features, please cite. The annotations are given as a with delimiter "," (comma) comprising with the following fields: ColumnĬrossComp-0001_01_bach_ouverture_no._1_in_c_major_bwv_1066_boure_iii.mp3īACH J.S.: Orchestral Suites Nos. To study the influence of the "artist effect", we also provide a numerical artist identifier to be used as a filter. We provide detailed annotations to the dataset comprising composer- and piece-related information (title, instrumentation) as well as performance-specific information (album name). If you publish results obtained using these annotations, please cite.
The following table provides more detailed information about the instrumentations in the dataset. The pieces stem from commercial recordings on 94 different albums and are played by 68 different interpreters. We included a large variety of instrumentations including orchestral works, piano pieces, and solo concertos as well as compositions for choir, organ, and harpsichord. Our datasets comprises 100 pieces by each of the 11 composers as shown in the following table: Class To allow for a comparison to state-of-the-art algorithms, we considered an 11-composer setting similar to the MIREX Audio Classical Composer Identification scenario, an annual evaluation contest of the Music Information Retrieval (MIR) community. Therefore, we focused on composers whose works frequently appear in concerts and on classical radio programs.
Furthermore, chroma-based audio features and automatically computed chord labels are available.įor the experiments in, we were interested in the typical repertoire of Western classical music. We provide annotations including composer- and piece-specific information as well as album information. For 11 different composers, the dataset contains each 100 tracks comprising different musical forms, keys, and tempi. It is compiled from commercial audio recordings, totalling 1100 tracks, where a track refers to the movement level of a piece. The dataset presented on this website served as basis for studying the composer identification task for Western classical music recordings in the PhD dissertation.