Article citationsMore>>

Reghunath, L. C., & Rajan, R. (2021). Predominant Instrument Recognition in Polyphonic Music Using Convolutional Recurrent Neural Networks. In M. Aramaki, K. Hirata, T. Kitahara, R. Kronland-Martinet, & Ystad, S. (Eds.), Music in AI Era (pp. 214-227). Springer.

has been cited by the following article:

• TITLE: Multi-Instrument Detection in Polyphonic Music with Cultural Instruments

  AUTHORS: Sovathanak Meas, Rezza Moieni

  KEYWORDS: Convolutional Neural Network, Multi-Instrument Detection, Cultural Instruments, Deep Learning, Multi-Label Classification

  JOURNAL NAME: Open Journal of Social Sciences, Vol.13 No.9, September 22, 2025

  ABSTRACT: The study adapts several machine-learning and deep-learning architectures to recognize 63 traditional instruments in weakly labelled, polyphonic audio synthesized from the proprietary Sound Infusion collection. Ten thousand 5s clips were algorithmically generated, features such as Mel-spectrograms, MFCCs, and VGGish embeddings were extracted, and six models were evaluated. The re-implemented Han et al. Convolutional Neural Network (CNN) attained the best result (micro F1 = 0.55; macro F1 = 0.50), approaching published performance on mainstream Instrument Recognition in Musical Audio Signals (IRMAS) data. Results highlight data scarcity and class imbalance as key obstacles for culturally diverse MIR.