Is CQT more suitable for monaural speech separation than STFT? an empirical study
This work addresses the problem of improving speech separation accuracy for audio processing applications, though it is incremental as it focuses on optimizing the front-end transform.
The study investigated whether the Constant Q Transform (CQT) is more suitable than the Short-Time Fourier Transform (STFT) for monaural speech separation, finding that CQT-based methods consistently outperformed STFT-based ones, achieving an average 0.4dB improvement in Signal-to-Distortion Ratio (SDR).
Short-time Fourier transform (STFT) is used as the front end of many popular successful monaural speech separation methods, such as deep clustering (DPCL), permutation invariant training (PIT) and their various variants. Since the frequency component of STFT is linear, while the frequency distribution of human auditory system is nonlinear. In this work we propose and give an empirical study to use an alternative front end called constant Q transform (CQT) instead of STFT to achieve a better simulation of the frequency resolving power of the human auditory system. The upper bound in signal-to-distortion (SDR) of ideal speech separation based on CQT's ideal ration mask (IRM) is higher than that based on STFT. In the same experimental setting on WSJ0-2mix corpus, we examined the performance of CQT under different backends, including the original DPCL, utterance level PIT, and some of their variants. It is found that all CQT-based methods are better than STFT-based methods, and achieved on average 0.4dB better performance than STFT based method in SDR improvements.