Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences

TL;DR

This paper investigates how sentence types influence the Lombard effect and speech intelligibility, comparing natural and grid sentences using corpora and conversion models, revealing trade-offs between speech quality and intelligibility enhancement.

Contribution

It introduces a comparative analysis of natural and grid sentences on Lombard effects and develops a conversion model, highlighting differences in speech quality and intelligibility in noisy conditions.

Findings

Grid sentences show stronger Lombard effects than natural sentences.

Natural sentences better preserve speech quality during enhancement.

Grid sentences may offer higher intelligibility due to pronounced Lombard effects.

Abstract

This study explores how sentence types affect the Lombard effect and intelligibility enhancement, focusing on comparisons between natural and grid sentences. Using the Lombard Chinese-TIMIT (LCT) corpus and the Enhanced MAndarin Lombard Grid (EMALG) corpus, we analyze changes in phonetic and acoustic features across different noise levels. Our results show that grid sentences produce more pronounced Lombard effects than natural sentences. Then, we develop and test a normal-to-Lombard conversion model, trained separately on LCT and EMALG corpora. Through subjective and objective evaluations, natural sentences are superior in maintaining speech quality in intelligibility enhancement. In contrast, grid sentences could provide superior intelligibility due to the more pronounced Lombard effect. This study provides a valuable perspective on enhancing speech communication in noisy environments.