Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech

TL;DR

This paper introduces a modified complex FDLP method that improves interpretability of speech modulation features and offers faster computation, enhancing automatic speech recognition feature extraction.

Contribution

The paper proposes a novel complex FDLP model that enhances interpretability of speech modulation features and significantly speeds up computation compared to traditional FDLP.

Findings

Improved interpretability of speech modulation features.

Significant speed-ups in FDLP computation.

Enhanced features for speech recognition.

Abstract

Conventional Frequency Domain Linear Prediction (FDLP) technique models the squared Hilbert envelope of speech with varied degrees of approximation which can be sampled at the required frame rate and used as features for Automatic Speech Recognition (ASR). Although previously the complex cepstrum of the conventional FDLP model has been used as compact frame-wise speech features, it has lacked interpretability in the context of the Hilbert envelope. In this paper, we propose a modification of the conventional FDLP model that allows easy interpretability of the complex cepstrum as temporal modulations in an all-pole model approximation of the power of the speech signal. Additionally, our "complex" FDLP yields significant speed-ups in comparison to conventional FDLP for the same degree of approximation.