A comparison of speech enhancement methods to extract Lombard speech in an external noise field

Abstract

The tendency of talkers to increase their vocal effort in noise, known as the Lombard effect, depends on many factors including the type and level of noise. To investigate the influence of these different factors while wearing hearing protectors, the Lombard effect needs to be elicited by an external noise field (e.g., loudspeakers) rather than the traditional method (e.g., headphones). While the Lombard speech produced may be contaminated by the eliciting noise, the alterations in the talker's voice are more realistically accounted for by such methodology. The problem of recovering sound-field elicited Lombard speech has not been studied extensively. In this study, two noise suppression techniques, direct waveform subtraction and adaptive filtering, are used to recover the Lombard speech produced in simulated conditions using a manikin. To assess the performance of the two methods, the size of noise reduction is compared and basic speech characteristics (e.g., pitch and energy) and objective quality and intelligibility measures (e.g., SII and STI) are extracted from the clean and enhanced Lombard speech. Preliminary results show that the simulated Lombard speech could be accurately recovered, which is useful to extend to speech production in noise with real talkers.