Minimum cost based phoneme class detection for improved iterative speech enhancement

It is known that degrading acoustic noise innuences speech quality across phoneme classes in a non-uniform manner. This results in variable quality performance for many speech enhancement algorithms in noisy environments. To address this, a hidden-Markov-model phoneme classiica-tion procedure is proposed which directs single channel speech enhancement across individual phoneme classes. The procedure performs broad phoneme class partitioning of noisy speech frames using a continuous-mixture hidden-Markov-model recognizer in conjunction with a cost based decision process. Cost functions are assigned which weigh errors between phoneme classes that are perceptually different (e.g., vowels versus fricatives, etc.). Once noisy speech frames are partitioned, iterative speech enhancement based on all-pole parameter estimation with inter and intra-frame spectral constraints (Auto:I,LSP:T) is employed. The phoneme class directed enhancement algorithm is evaluated using TIMIT speech data, and shown to result in substantial improvement in objective speech quality over a range of signal-to-noise ratios and individual phoneme classes. The algorithm is also shown to possess consistent quality improvement in a speaker independent scenario.