mjhydri
Ph.D. Candidate at Audio Information Research (AIR) Lab - University of Rochester
University of RochesterRochester, NY
Pinned Repositories
1D-StateSpace
This repository contains the implementation of an efficient joint beat, downbeat, tempo, and meter tracking system using a compact 1D probabilistic state space and a jump-back reward technique. ICASSP 2022.
BeatNet
BeatNet is state-of-the-art (Real-Time) and Offline joint music beat, downbeat, tempo, and meter tracking system using CRNN and particle filtering. (ISMIR 2021's paper implementation).
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
lhvqt
Frontend filterbank learning module with HVQT initialization capabilities.
online-music-structure-segmentation
Singing-Vocal-Beat-Tracking
This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBERT pre-trained speech models to create vocal embeddings and trains linear multi-head self-attention layers on top of them to extract vocal beat activations. Then, it uses HMM decoder to infer signing beats and tempo.
sparse-analytic-filters
Code for the paper "Learning Sparse Analytic Filters for Piano Transcription".
torchaudio-augmentations
Audio transformations library for PyTorch
transformer-in-transformer
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
mjhydri's Repositories
mjhydri/BeatNet
BeatNet is state-of-the-art (Real-Time) and Offline joint music beat, downbeat, tempo, and meter tracking system using CRNN and particle filtering. (ISMIR 2021's paper implementation).
mjhydri/1D-StateSpace
This repository contains the implementation of an efficient joint beat, downbeat, tempo, and meter tracking system using a compact 1D probabilistic state space and a jump-back reward technique. ICASSP 2022.
mjhydri/Singing-Vocal-Beat-Tracking
This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBERT pre-trained speech models to create vocal embeddings and trains linear multi-head self-attention layers on top of them to extract vocal beat activations. Then, it uses HMM decoder to infer signing beats and tempo.
mjhydri/online-music-structure-segmentation
mjhydri/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
mjhydri/lhvqt
Frontend filterbank learning module with HVQT initialization capabilities.
mjhydri/sparse-analytic-filters
Code for the paper "Learning Sparse Analytic Filters for Piano Transcription".
mjhydri/torchaudio-augmentations
Audio transformations library for PyTorch
mjhydri/transformer-in-transformer
Implementation of Transformer in Transformer, pixel level attention paired with patch level attention for image classification, in Pytorch
mjhydri/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.