BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer
CoRR(2023)
摘要
Many deep learning models have achieved dominant performance on the offline
beat tracking task. However, online beat tracking, in which only the past and
present input features are available, still remains challenging. In this paper,
we propose BEAt tracking Streaming Transformer (BEAST), an online joint beat
and downbeat tracking system based on the streaming Transformer. To deal with
online scenarios, BEAST applies contextual block processing in the Transformer
encoder. Moreover, we adopt relative positional encoding in the attention layer
of the streaming Transformer encoder to capture relative timing position which
is critically important information in music. Carrying out beat and downbeat
experiments on benchmark datasets for a low latency scenario with maximum
latency under 50 ms, BEAST achieves an F1-measure of 80.04
in downbeat, which is a substantial improvement of about 5 and 13 percentage
points over the state-of-the-art online beat and downbeat tracking model.
更多查看译文
关键词
Beat Tracking,Transformer,Online Processing,Low Latency
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要