Search Results for author:
Found 11 papers, 8 papers with code
A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation
Despite its simplicity, benchmark results show our system's note estimation to be substantially better than a comparable baseline, and its frame-level accuracy to be only marginally below those of specialized state-of-the-art AMT systems.
Ranked #3 on
Music Transcription
on Slakh2100
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end.
Ranked #27 on
Music Source Separation
on MUSDB18
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction
Based on this idea, we drive the separator towards outputs deemed as realistic by discriminator networks that are trained to tell apart real from separator samples.
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling
In comparison to TCN and Wavenet, our network consistently saves memory and computation time, with speed-ups for training and inference of over 4x in the audio generation experiment in particular, while achieving a comparable performance in all tasks.
Ranked #2 on
Music Modeling
on Nottingham
End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model
Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications.
Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages
This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment.
Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators
We apply our method to image generation, image segmentation and audio source separation, and obtain improved performance over a standard GAN when additional incomplete training examples are available.
Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio
In this paper, we show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variables, and is prone to collapse the static latent variable.
Jointly Detecting and Separating Singing Voice: A Multi-Task Approach
A main challenge in applying deep learning to music processing is the availability of training data.
An Augmented Lagrangian Method for Piano Transcription using Equal Loudness Thresholding and LSTM-based Decoding
A central goal in automatic music transcription is to detect individual note events in music recordings.
Structured Dropout for Weak Label and Multi-Instance Learning and Its Application to Score-Informed Source Separation
Many success stories involving deep neural networks are instances of supervised learning, where available labels power gradient-based learning methods.
