Saved in:
Bibliographic Details
Main Authors: Kim, Yonghyun, Lerch, Alexander
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.14122
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914978113519616
author Kim, Yonghyun
Lerch, Alexander
author_facet Kim, Yonghyun
Lerch, Alexander
contents 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 white noise at various Signal-to-Noise Ratio (SNR) levels on state-of-the-art APT models and evaluates the performance of the Onsets and Frames model when trained on noise-augmented data. We hope this research provides valuable insights as preliminary work toward developing transcription models that maintain consistent performance across a range of acoustic conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14122
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation
Kim, Yonghyun
Lerch, Alexander
Sound
Artificial Intelligence
Information Retrieval
Machine Learning
Audio and Speech Processing
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 white noise at various Signal-to-Noise Ratio (SNR) levels on state-of-the-art APT models and evaluates the performance of the Onsets and Frames model when trained on noise-augmented data. We hope this research provides valuable insights as preliminary work toward developing transcription models that maintain consistent performance across a range of acoustic conditions.
title Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation
topic Sound
Artificial Intelligence
Information Retrieval
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2410.14122