An Investigation of the Effectiveness of Phase for Audio Classification
arXiv:2110.02878 · doi:10.1109/ICASSP43922.2022.9746037
Abstract
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.
arXiv comment5 pages, 3 figures
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- VoxCeleb: a large-scale speaker identification dataset
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Language Modeling with Gated Convolutional Networks
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- When Does Label Smoothing Help?
- Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
- Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
- Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions
- Multiclass Language Identification using Deep Learning on Spectral Images of Audio Signals
- LEAF: A Learnable Frontend for Audio Classification