Text-directed speech enhancement using phoneme classification and feature map constrained vector quantization

This paper presents and evaluates a novel text-directed speech enhancement algorithm for usage in non-real-time applications. In our approach, the text of the intended dialogue is used to partition noisy speech into regions of broad phoneme classifications. Classes considered include stops, fricatives, affricates, nasals, vowels, semivowels, diphthongs and silence. These partitions are then used to direct a new vector quantizer based enhancement scheme in which class directed constraints are applied to improve speech quality. Objective enhancement evaluations conducted across 100 sentences of the TIMIT database indicate consistent improvement in speech quality for actual helicopter fly-by noise, aircraft cockpit noise, and automobile highway noise at signal-to-noise ratios ranging from -5 to 10 dB. Subjective quality assessment was conducted in the form of an A-B comparison test. Results of these evaluations demonstrate that, for wideband noise distortion, the proposed algorithm is preferred over unprocessed noisy speech more than 2 to 1, while the proposed algorithm is preferred over spectral subtraction processed speech by more than 3 to 1