An objective measure of speech intelligibility is required in order to guess whether or not the written transcription made from an intercept recording is an accurate representation of the talker's speech or if it is influenced by the views of the transcribers. Usually, a lawful interception can have two types of distortion: the distortions that affect the speech signal itself (called speech distortion) and the distortions that affect the background noise (called noise distortion). Unfortunately, the forensic expert does not have the original clean signal, therefore, must make its assessment based on the only available signal. This paper addresses the issue by experimentally comparing three different objective approaches, that are the Signal-to-Noise ratio weighted with the curves "A" (S/NA), the Articulation Index (AI) and the Speech Transmission Index (STI) to evaluate the signal intelligibility against a corpus for which the voice intelligibility is known. The approaches are tested with three different types of noise and the results were compared with the speech intelligibility scores measured by subjective tests. Measures based on STI have proven to be reliable for predicting the intelligibility in forensic applications.
展开▼
