Lemon Inc. (20240404494). IMPLEMENTING AUTOMATIC MUSIC AUDIO TRANSCRIPTION

IMPLEMENTING AUTOMATIC MUSIC AUDIO TRANSCRIPTION

Organization Name

Lemon Inc.

Inventor(s)

Wei Tsung Lu of Los Angeles CA (US)

Ju-Chiang Wang of Los Angeles CA (US)

Yun-Ning Hung of Culver City CA (US)

IMPLEMENTING AUTOMATIC MUSIC AUDIO TRANSCRIPTION

This abstract first appeared for US patent application 20240404494 titled 'IMPLEMENTING AUTOMATIC MUSIC AUDIO TRANSCRIPTION

Original Abstract Submitted

the present disclosure describes techniques for implementing automatic music audio transcription. a deep neural network model may be configured. the deep neural network model comprises a spectral cross-attention sub-model configured to project a spectral representation of each time step t, denoted as st, into a set of latent arrays at the time step t, denoted as �, h representing an h-th iteration. the deep neutral network model comprises a plurality of latent transformers configured to perform self-attention on the set of latent arrays �. the deep neural network model further comprises a set of temporal transformers configured to enable communications between any pairs of latent arrays �at different time steps. training data may be augmented by randomly mixing a plurality of types of datasets comprising a vocal dataset and an instrument dataset. the deep neural network model may be trained using the augmented training data.