ClassTalk system for predicting and auralizing speech in noise with reverberation in classrooms

This paper discusses and demonstrates the ClassTalk system for predicting, visualizing and auralizing speech in noise with reverberation in classrooms. The classroom can contain a speech-reinforcement system (SRS). Male or female speech sources, SRS loudspeakers and overhead, slide or digital projectors, or ventilation-noise sources, can have four output levels. Empirical models are used to predict speech and noise levels, and Early Decay Times, from which Speech Transmission Index (STI) and Speech Intelligibility (SI) are calculated. ClassTalk visualizes the floor-plan, speech- and noise-source positions, and the receiver position. The user can walk through the room at will. In real time five quantities, background-noise level, speech level, signal-to-noise difference, STI and SI, are displayed along with occupied and unoccupied reverberation times. The sound module auralizes male or female speech mixed with the relevant noise signals, with predicted, frequency-varying reverberation superimposed using MaxxVerb. Technical issues related to the development of the sound module are discussed. The potential of the systems auralization module for demonstrating the effects of the acoustical environment and its control on speech is discussed and demonstrated.