Deep Embeddings For Robust User-based Amateur Vocal Percussion Classification

Abstract

Vocal Percussion Transcription (VPT) is concerned with the automatic detection and classification of vocal percussion sound events, allowing music creators and producers to sketch drum lines on the fly. Classifier algorithms in VPT systems learn best from small user-specific datasets, which usually restrict modelling to small input feature sets to avoid data overfitting. This study explores several deep supervised learning strategies to obtain informative feature sets for amateur vocal percussion classification. We evaluated the performance of these sets on regular vocal percussion classification tasks and compared them with several baseline approaches including feature selection methods and a speech recognition engine. These proposed learning models were supervised with several label sets containing information from four different levels of abstraction: instrument-level, syllable-level, phoneme-level, and boxeme-level. Results suggest that convolutional neural networks supervised with

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydelgado2022deep

Related papers

• Robust Vocal Quality Feature Embeddings For Dysphonic Voice Detection (2022)7.16
• Similarity Measures For Vocal-based Drum Sample Retrieval Using Deep Convolutional Auto-encoders (2018)2.26
• Human Vocal Sentiment Analysis (2019)0.00
• Deep Audio-visual Singing Voice Transcription Based On Self-supervised Learning Models (2023)0.00
• Transfer Learning For Improving Singing-voice Detection In Polyphonic Instrumental Music (2020)7.16
• Deepvox: Discovering Features From Raw Audio For Speaker Recognition In Non-ideal Audio Signals (2020)0.00
• A Simple Fusion Of Deep And Shallow Learning For Acoustic Scene Classification (2018)0.00
• Personalized Acoustic Modeling By Weakly Supervised Multi-task Deep Learning Using Acoustic Tokens Discovered From Unlabeled Data (2017)2.26