Author: Matti Ryynänen,
homepage
Last modified: September 2006
M. Ryynänen and A. Klapuri, "Automatic Bass Line Transcription from Streaming Polyphonic Audio," in Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'07), Honolulu, Hawaii, USA, April 2007.
We propose a method for the automatic transcription of the bass line in polyphonic music. The method uses a multiple-F0 estimator as a front-end and this is followed by acoustic and musicological models. The acoustic modeling consists of separate models for bass notes and rests. The musicological model estimates the key and determines probabilities for the transitions between notes using a conventional bigram or a variable-order Markov model. The transcription is obtained with Viterbi decoding through the note and rest models. In addition, a causal algorithm is presented which allows transcription of streaming audio. The method was evaluated using 87 minutes of music from the RWC Popular Music Database. Recall and precision rates of 64% and 60%, respectively, were achieved for discrete note events.
The transcription method produces a MIDI file containing the transcribed bass line. The following sound examples include the acoustic input signal in the left channel and the transcribed bass line (synthesized directly from the output MIDI file) in the right channel.
For each example, we show a score image of the transcription. The score images are automatically generated from the transcription MIDI files by using Lilypond music score typesetter. Please notice that the notes are not temporally quantized so that the score typesetting could be done unambiguously. The score images give some idea on the transcriptions, but they are not accurate in timing and assume time signature to be always 4/4.
Most of the following transcription examples are from the RWC (Real World Computing) popular music database which contains 100 acoustic recordings of typical pop songs [1]. The same database was used in the development and the evaluation of the transcription method. See RWC music database homepage for additional information on the music performance examples. The authors of the RWC database kindly granted a permission to set the following RWC input music files available.
Some other transcription examples are also included. The sound samples are from artists' web pages or web-store sound samples. Please notice that this copyrighted material is here used only for research purposes for short demonstrations.
[1] M. Goto, H. Hashiguchi, T. Nishimura, and R. Oka, "RWC music database: Popular, classical, and jazz music databases," in Proc. 3rd International Conference on Music Information Retrieval, Oct. 2002.
| RWC music database: | ||
| HORO (RWC-MDB-P-2001 No. 3) | mp3 | score |
| Koino Ver.2.4 (RWC-MDB-P-2001 No. 5) | mp3 | score |
| Tokimeki no syunkan (RWC-MDB-P-2001 No. 20) | mp3 | score |
| Feeling In My Heart (RWC-MDB-P-2001 No. 21) | mp3 | score |
| Koi ni ochiru jikan ni kansuru kousatsu (RWC-MDB-P-2001 No. 22) | mp3 | score |
| What could I do for you (RWC-MDB-P-2001 No. 32) | mp3 | score |
| Senro wa tsuzukuyo (RWC-MDB-P-2001 No. 46) | mp3 | score |
| Haru ga kurukara (RWC-MDB-P-2001 No. 52) | mp3 | score |
| For You (RWC-MDB-P-2001 No. 61) | mp3 | score |
| Life (RWC-MDB-P-2001 No. 94) | mp3 | score |
| Other song samples: | ||
| Billy Sheehan: Under My Thumb | mp3 | score |
| Jazzanova: Hanazono | mp3 | score |
| Niacin: Slapped Silly | mp3 | score |
| Planet X: Ignotus Per Ignotum | mp3 | score |
