2007:Query by Singing/Humming
This is only a very basic draft version of a task proposal. Once more people show interest we can fill in the details.
The goal of the Query-by-Singing/Humming (QBSH) task is the evaluation of MIR systems that take as query input queries sung or hummed by real-world users. More information can be found in:
Please feel free to edit this page.
The MIREX2006 corpus contributed by Roger Jang should be included:
To build a large test set which can reflect real-world queries, it is also suggested that every participant makes a contribution to the evaluation corpus. We can provide the record tool and some midi utilities if necessary.
Classic QBSH evaluation:
- Input: human singing/humming snippets (.wav)
- Database: ground-truth and noise midi files(which are monophonic)
- Output: candidate list.
- Evaluation: Mean Reciprocal Rank (MMR) and Top-X hit rate.
Rainer Typke also suggests a hybrid symbolic/audio query by humming task which combines a few different algorithm modules (like mono/poly phonic transcriber and rhythm/melody matcher) and evaluates them in a more complex database composed of polyphonic audio files. It could be further discussed.
Please add your name and e-mail address to this list
- Xiao Wu (xwu at hccl dot ioa dot ac dot cn)