Paper page - A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation

Source: https://huggingface.co/papers/2203.09893 Published on Mar 18, 2022

Abstract

A lightweight neural network for musical instrument transcription achieves high frame-level note accuracy across multiple instruments and is more memory-efficient than specialized systems.

Automatic Music Transcription (AMT) has been recognized as a key enabling technology with a wide range of applications. Given the task’s complexity, best results have typically been reported for systems focusing on specific settings, e.g. instrument-specific systems tend to yield improved results overinstrument-agnosticmethods. Similarly, higher accuracy can be obtained when only estimating frame-wise f_0 values and neglecting the harder note event detection. Despite their high accuracy, such specialized systems often cannot be deployed in the real-world. Storage and network constraints prohibit the use of multiple specialized models, while memory and run-time constraints limit their complexity. In this paper, we propose a lightweightneural networkformusical instrument transcription, which supportspolyphonic outputsand generalizes to a wide variety of instruments (including vocals). Our model is trained to jointly predictframe-wise onsets,multipitchandnote activations, and we experimentally show that this multi-output structure improves the resultingframe-level note accuracy. 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. With this work we hope to encourage the community to further investigatelow-resource,instrument-agnosticAMT systems.

View arXiv pageView PDFGitHub5.77kautoAdd to collection

Get this paper in your agent:

hf papers read 2203\.09893

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper3

#### spotify/basic-pitch UpdatedSep 12, 2023 • 31 #### AEmotionStudio/basic-pitch-onnx-models #### TTSCloneAPI/basic-pitch Updated15 days ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2203.09893 in a dataset README.md to link it from this page.

Spaces citing this paper18

Browse 18 spaces citing this paper## Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.