The "Lombard effect" describes how humans modify their speech in noisy environments to make it more intelligible. The present work analyzes Normal and Lombard speech from multiple speakers in an unsupervised context, using meaningful acoustic criteria for speech classification (according to voicing and stationarity) and evaluation (using loudness and intelligibility). These acoustic analyses using generalized classes offer alternative and informative interpretations of the Lombard effect. For example, the Lombard increase in intelligibility is shown to be isolated primarily to voiced speech. Also, while transients are shown to be less intelligible overall, the Lombard effect does not appear to distinguish between stationary and transient speech. In addition to these analyses, following recently published results illustrating that Lombard spectral modifications account for the largest increases in intelligibility, this work also examines spectral envelope transformation to improve speech intelligibility. In particular, speaker-dependent Normal-to-Lombard correction filters are estimated and, when applied in transformation, shown to yield higher overall objective intelligibility than Normal, and even Lombard, speech.

Index Terms: Lombard effect, spectral transformation