Abstract: A hearing application suite includes enhancement and training for listening and hearing of prerecorded speech, extemporaneous voice communication, and non-speech sound. Enhancement includes modification of audio according to audiometric data representing subjective hearing abilities of the user, display of textual captions contemporaneously with the display of the audiovisual content, user-initiated repeating of a most recently played portion of the audiovisual content, user-controlled adjustment of the rate of playback of the audiovisual content, user-controlled dynamic range compression/expansion, and user controlled noise reduction. Training includes testing the user's ability to discern speech and/or various other qualities of audio with varying degrees of quality.

Abstract: The apparatus for the recognition of speech comprises an acoustic preprocessor, a visual preprocessor, and a speech classifier that operates on the acoustic and visual preprocessed data. The acoustic preprocessor comprises a log mel spectrum analyzer that produces an equal mel bandwidth log power spectrum. The visual processor detects the motion of a set of fiducial markers on the speaker's face and extracts a set of normalized distance vectors describing lip and mouth movement. The speech classifier uses a multilevel time-delay neural network operating on the preprocessed acoustic and visual data to form an output probability distribution that indicates the probability of each candidate utterance having been spoken, based on the acoustic and visual data.