arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.05689cs.SDcs.LGeess.AS
收藏

注意力作为学习时间不变音频的视角

Attention as a Perspective for Learning Tempo-invariant Audio Queries

Johannes Kepler University Linz(林茨约翰内斯·开普勒大学);Charles University(查理大学)

Matthias Dorfer, Jan Hajič, Gerhard Widmer

摘要:

当前的音频--通过多模态嵌入空间学习的乐谱检索模型使用卷积神经网络,其输入音频窗口大小固定。根据查询演奏的节奏,该窗口捕获或多或少的音乐内容,而乐谱中的音符头密度在很大程度上与节奏无关。在这项工作中,我们解决了这种差异与软注意力机制,它允许模型编码的音频摘录,最相关的高效查询代码的那些部分。对古典钢琴音乐的实验结果表明,注意有利于提取绩效,并表现出直观的吸引力行为。

英文摘要:

Current models for audio--sheet music retrieval via multimodal embedding space learning use convolutional neural networks with a fixed-size window for the input audio. Depending on the tempo of a query performance, this window captures more or less musical content, while notehead density in the score is largely tempo-independent. In this work we address this disparity with a soft attention mechanism, which allows the model to encode only those parts of an audio excerpt that are most relevant with respect to efficient query codes. Empirical results on classical piano music indicate that attention is beneficial for retrieval performance, and exhibits intuitively appealing behavior.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑