# Experimental investigation on STFT phase representations for deep learning-based dysarthric speech detection

arXiv: https://arxiv.org/abs/2110.03283 · HTML: https://mlsanity.com/paper/2110.03283/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2021.

## Built on by (most cited first, 7 of 7)

- [OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation](https://mlsanity.com/paper/2310.02422/) (2023)
- [Impact of Speech Mode in Automatic Pathological Speech Detection](https://mlsanity.com/paper/2406.09968/) (2024)
- [Graph Neural Networks for Parkinsons Disease Detection](https://mlsanity.com/paper/2409.07884/) (2024)
- [Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection](https://mlsanity.com/paper/2409.17276/) (2024)
- [Speaker Embeddings as Individuality Proxy for Voice Stress Detection](https://mlsanity.com/paper/2306.05915/) (2023)
- [Selfsupervised learning for pathological speech detection](https://mlsanity.com/paper/2406.02572/) (2024)
- [Investigating the Effects of Diffusion-based Conditional Generative Speech Models Used for Speech Enhancement on Dysarthric Speech](https://mlsanity.com/paper/2412.13933/) (2024)

## Abstract (arXiv)

Mainstream deep learning-based dysarthric speech detection approaches typically rely on processing the magnitude spectrum of the short-time Fourier transform of input signals, while ignoring the phase spectrum. Although considerable insight about the structure of a signal can be obtained from the magnitude spectrum, the phase spectrum also contains inherent structures which are not immediately apparent due to phase discontinuity. To reveal meaningful phase structures, alternative phase representations such as the modified group delay (MGD) and instantaneous frequency (IF) spectra have been investigated in several applications. The objective of this paper is to investigate the applicability of the unprocessed phase, MGD, and IF spectra for dysarthric speech detection. Experimental results show that dysarthric cues are present in all considered phase representations. Further, it is shown that using phase representations as complementary features to the magnitude spectrum is beneficial for deep learning-based dysarthric speech detection, with the combination of magnitude and IF spectra yielding a high performance. The presented results should raise awareness in the research community about the potential of the phase spectrum for dysarthric speech detection and motivate research into novel architectures which optimally exploit magnitude and phase information.