Posts
-
I am elated to announce that I have successfully defended by Ph.D. thesis titled Learning to Manipulate Latent Representations of Deep Generative Models last December (2020). I have had a great journey through grad school at Georgia Tech over the last ~6 years where I have learnt a lot and met some really incredible people. Looking forward to the next phase of my life now.
10 Jan 2021
-
Our review paper titled “An Interdisciplinary Review of Music Performance Analysis” was published in the TISMIR journal as a part of the Special Collection: 20th Anniversary of ISMIR. The full paper is available online here.
23 Nov 2020
-
Had the pleasure of attending the all-virtual 21st ISMIR conference. Even though it was a bummer to not be able to visit Montréal again, the amazing job done by the conference organizers and the warm ISMIR community made sure the virtual conference was as close as possible to the in-person event. We presented our work on the dMelodies dataset and on score-informed networks for music performance assessment. I was also pretty stoked to be amongst the best reviewer awardees.
19 Oct 2020
-
Blog post summarizing my recent journal article on attribute-based regularization of VAEs.
14 Aug 2020
-
My paper titled “Attribute-based Regularization of Latent Spaces for Variational Auto-Encoders”, was published in Neural Computing and Applications. I explore a new supervised training method to create structured latent spaces where specific continuous-valued attributes are forced to be encoded along specific dimensions of the latent space. The full paper is available here. Alternatively, the ArXIV pre-print of the article can be accessed here.
07 Aug 2020
-
Had a great time attending the 20th ISMIR (International Society for Music Information Retrieval) conference at Delft, Netherlands to present my work on models for music inpainting. The full paper is available here.
In addition, our joint work surveying Music Performance Analysis was also published as one of the four 20th anniversary papers.
04 Nov 2019
-
Our paper titled “Explicitly conditioned melody generation: A case study with interdependent RNNs” was published in the 7th MUME (International Workshop on Musical Metacreation) workshop. This research presents a comparative analysis of RNN-based music generation models when conditioned with explicit musical information. A blog post summarizing the above paper can be found here and the full paper is available here.
17 Jun 2019
-
Attended the ICML workshop on Machine Learning for Music Discovery to present my work on regularizing latent spaces of VAE (Variational Auto-Encoder)-based models for automatic music generation. The proposed method can provide users with explicit control over musical attributes such as note density, rhythmic complexity, etc., and thereby, help design intuitive musical interfaces to enhance creative workflows. The full paper is available here.
16 Jun 2019
-
Attended the NeurIPS (Neural Information Processing Systems) 2018 conference at Montréal, Canada as a part of the Sony CSL team. We were presenting a demo of our model-agnostic web-based interface that allows users to compose symbolic music in an interactive way using generative models for music inpainting.
01 Dec 2018
-
Our paper titled “Analysis of Objective Descriptors for Music Performance Assessment”, was published as in the International Conference on Music Perception and Cognition (ICMPC). In this paper we analyze the impact of several hand-designed and standard features on the automatic evaluation of music performance assessments. The full paper is available here.
01 Aug 2018
-
Our paper titled “Assessment of Student Music Performances using Deep Neural Networks”, was published as in the Applied Sciences Journal, Special Issue on “Digital Audio and Image Processing with Focus on Music Research”. We explore the possibility of using Deep Neural Networks (DNNs) to assess student music performances across several subjective criteria like Musicality, Note Accuracy, Rhytmic Accuracy and Tone Quality. The experimental results show that DNNs outperform previously used methods and more so for abstract concepts like Musicality. A blog post summarizing the above paper can be found here and the full paper is available here.
26 Jun 2018
Blog-style article with preliminary experiments and findings towards developing deep learning paradigms for style transfer in symbolic music data
08 Jan 2018
-
My paper titled “A Dataset and Method for Electric Guitar Solo Detection in Rock Music”, which was published as a Conference Paper at the 2017 AES (Audio Engineering Society) International Conference on Semactic Audio, was also amongst the featured papers in the overview article published in the 2017 Journal of the Audio Engineering Society. A blog post summarizing the above paper can be found here and the full paper is available here.
02 Jan 2018