ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

Knowledge Distillation for Singing Voice Detection

Soumava Paul, Gurunath Reddy M, K. Sreenivasa Rao, Partha Pratim Das

Singing Voice Detection (SVD) has been an active area of research in music information retrieval (MIR). Currently, two deep neural network-based methods, one based on CNN and the other on RNN, exist in literature that learn optimized features for the voice detection (VD) task and achieve state-of-the-art performance on common datasets. Both these models have a huge number of parameters (1.4M for CNN and 65.7K for RNN) and hence not suitable for deployment on devices like smartphones or embedded sensors with limited capacity in terms of memory and computation power. The most popular method to address this issue is known as knowledge distillation in deep learning literature (in addition to model compression) where a large pre-trained network known as the teacher is used to train a smaller student network. Given the wide applications of SVD in music information retrieval, to the best of our knowledge, model compression for practical deployment has not yet been explored. In this paper, efforts have been made to investigate this issue using both conventional as well as ensemble knowledge distillation techniques.

doi: 10.21437/Interspeech.2021-636

Cite as: Paul, S., M, G.R., Rao, K.S., Das, P.P. (2021) Knowledge Distillation for Singing Voice Detection. Proc. Interspeech 2021, 4159-4163, doi: 10.21437/Interspeech.2021-636

  author={Soumava Paul and Gurunath Reddy M and K. Sreenivasa Rao and Partha Pratim Das},
  title={{Knowledge Distillation for Singing Voice Detection}},
  booktitle={Proc. Interspeech 2021},