Complex-Valued Restricted Boltzmann Machine for Direct Speech Parameterization from Complex Spectra

TL;DR

This paper introduces the complex-valued restricted Boltzmann machine (CRBM), a novel model that directly encodes complex spectra for speech feature extraction, outperforming traditional methods in speech coding tasks.

Contribution

The paper presents the CRBM, extending RBMs to handle complex-valued data with real-imaginary connections, enabling direct complex spectrum encoding and decoding for speech processing.

Findings

CRBM outperforms traditional speech coding methods.

CRBM effectively encodes complex spectra into binary latent features.

The model improves speech feature extraction by utilizing phase information.

Abstract

This paper describes a novel energy-based probabilistic distribution that represents complex-valued data and explains how to apply it to direct feature extraction from complex-valued spectra. The proposed model, the complex-valued restricted Boltzmann machine (CRBM), is designed to deal with complex-valued visible units as an extension of the well-known restricted Boltzmann machine (RBM). Like the RBM, the CRBM learns the relationships between visible and hidden units without having connections between units in the same layer, which dramatically improves training efficiency by using Gibbs sampling or contrastive divergence (CD). Another important characteristic is that the CRBM also has connections between real and imaginary parts of each of the complex-valued visible units that help represent the data distribution in the complex domain. In speech signal processing, classification and generation features are often based on amplitude spectra (e.g., MFCC, cepstra, and mel-cepstra) even if they are calculated from complex spectra, and they ignore phase information. In contrast, the proposed feature extractor using the CRBM directly encodes the complex spectra (or another complex-valued representation of the complex spectra) into binary-valued latent features (hidden units). Since the visible-hidden connections are undirected, we can also recover (decode) the complex spectra from the latent features directly. Our speech coding experiments demonstrated that the CRBM outperformed other speech coding methods, such as methods using the conventional RBM, the mel-log spectrum approximate (MLSA) decoder, etc.