Related papers: MT3: Multi-Task Multitrack Music Transcription

Scarcity of parallel sentence pairs is a major challenge for training high quality neural machine translation (NMT) models in bilingually low-resource scenarios, as NMT is data-hungry. Multi-task learning is an elegant approach to inject…

This paper proposes a neural network that performs audio transformations to user-specified sources (e.g., vocals) of a given audio track according to a given description while preserving other sources not mentioned in the description. Audio…

Symbolic Music Emotion Recognition(SMER) is to predict music emotion from symbolic data, such as MIDI and MusicXML. Previous work mainly focused on learning better representation via (mask) language model pre-training but ignored the…

Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly…

With the increasing prevalence of recorded human speech, spoken language understanding (SLU) is essential for its efficient processing. In order to process the speech, it is commonly transcribed using automatic speech recognition…

Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains largely unexplored. This study investigates the impact of…

In the age of music streaming platforms, the task of automatically tagging music audio has garnered significant attention, driving researchers to devise methods aimed at enhancing performance metrics on standard datasets. Most recent…

In recent years, thanks to advances in automatic music transcription (AMT), several large-scale datasets of automatically transcribed piano solo music have been released. While these datasets undoubtedly offer extensive material for…

The increasing adoption of natural language processing (NLP) models across industries has led to practitioners' need for machine learning systems to handle these models efficiently, from training to serving them in production. However,…

Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for many computer vision tasks. The effective adoption of MTL…

One of the challenging problems in Music Information Retrieval is the acquisition of enough non-copyrighted audio recordings for model training and evaluation. This study compares two Transformer-based neural network models for chord…

Adapter parameters provide a mechanism to modify the behavior of machine learning models and have gained significant popularity in the context of large language models (LLMs) and generative AI. These parameters can be merged to support…

We present the Inverse Drum Machine, a novel approach to Drum Source Separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervised methods that require isolated stem recordings for…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Optical Music Recognition (OMR) is concerned with transcribing sheet music into a machine-readable format. The transcribed copy should allow musicians to compose, play and edit music by taking a picture of a music sheet. Complete…

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the…

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…

Self-attention is an attention mechanism that learns a representation by relating different positions in the sequence. The transformer, which is a sequence model solely based on self-attention, and its variants achieved state-of-the-art…

Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…

Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…