Enhancing automatic music transcription of Thai xylophone music performed with hard mallets: a deep learning approach and comparative analysis

Puntos clave

• Automatic music transcription accuracy significantly improved for Thai xylophone music with deep learning techniques.
• The study highlights a notable increase in transcription performance over traditional methods, achieving a 25% enhancement.
• Comparative analysis was conducted using various deep learning models to assess their effectiveness on different music segments.
• This work indicates promising potential for future applications in music technology and audio processing.