We studied the problem of automatic music transcription (AMT) for polyphonic music. AMT is an important task for music information retrieval because AMT results enable retrieving musical pieces, high-level annotation, demixing, etc. We attempted to transcribe a part played by an instrument specified by users (specified part tracking). Only two timbre models are required in the specified part tracking to identify the specified musical instrument even when the number of instruments increases. This transcription is formulated into a time-series classification problem with multiple features. We furthermore attempted to automatically estimate weights of the features, because the importance of these features varies for each musical signal. We estimated quasi-optimal weights of the features using a genetic algorithm for each musical signal. We tested our AMT system using trio stereo musical signals. Accuracies with our feature weighting method were 69.8% on average, whereas those without feature weighting were 66.0%.