Enhancing speech intelligibility: interactions among context, modality, speech style, and masker

PURPOSE: The authors sought to investigate interactions among intelligibility-enhancing speech cues (i.e., semantic context, clearly produced speech, and visual information) across a range of masking conditions.

METHOD: Sentence recognition in noise was assessed for 29 normal-hearing listeners. Testing included semantically normal and anomalous sentences, conversational and clear speaking styles, auditory-only (AO) and audiovisual (AV) presentation modalities, and 4 different maskers (2-talker babble, 4-talker babble, 8-talker babble, and speech-shaped noise).

RESULTS: Semantic context, clear speech, and visual input all improved intelligibility but also interacted with one another and with masking condition. Semantic context was beneficial across all maskers in AV conditions but only in speech-shaped noise in AO conditions. Clear speech provided the most benefit for AV speech with semantically anomalous targets. Finally, listeners were better able to take advantage of visual information for meaningful versus anomalous sentences and for clear versus conversational speech.

CONCLUSION: Because intelligibility-enhancing cues influence each other and depend on masking condition, multiple maskers and enhancement cues should be used to accurately assess individuals' speech-in-noise perception.