An Investigation of the Effectiveness of Phase for Audio Classification
An Investigation of the Effectiveness of Phase for Audio Classification
复制标题
DOI：
10.1109/icassp43922.2022.9746037
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Shunsuke Hidaka;Kohei Wakamiya;T. Kaburagi
中科院分区：
文献类型：
--
作者：
Shunsuke Hidaka;Kohei Wakamiya;T. Kaburagi
虽然对数振幅梅尔频谱图已广泛用作基于深度学习的语音处理的特征表示，但语音频谱的另一个方面（即相位信息）最近在语音增强和源分离等任务中显示出了有效性。在这项研究中，我们广泛研究了八个音频分类任务中包含信号相位信息的有效性。我们构建了一个可学习的前端，可以基于具有类似梅尔频率轴的时频表示来计算相位及其导数。结果，实验结果表明音高检测、乐器检测、语言识别、说话人识别和鸟鸣检测的性能显着提高。另一方面，当使用瞬时频率时，某些任务观察到对记录条件的过度拟合。结果表明，在音频分类中，相邻元素的相位值之间的关系比相位本身更重要。
While log-amplitude mel-spectrogram has widely been used as the feature representation for processing speech based on deep learning, the effectiveness of another aspect of speech spectrum, i.e., phase information, was shown recently for tasks such as speech enhancement and source separation. In this study, we extensively investigated the effectiveness of including phase information of signals for eight audio classification tasks. We constructed a learnable front-end that can compute the phase and its derivatives based on a time-frequency representation with mel-like frequency axis. As a result, experimental results showed significant performance improvement for musical pitch detection, musical instrument detection, language identification, speaker identification, and birdsong detection. On the other hand, overfitting to the recording condition was observed for some tasks when the instantaneous frequency was used. The results implied that the relationship between the phase values of adjacent elements is more important than the phase itself in audio classification.