Morphological constrained feature enhancement with adaptive cepstral compensation (MCE-ACC) for speech recognition in noise and Lombard effect

The use of present-day speech recognition techniques in many practical applications has demonstrated the need for improved algorithm formulation under varying acoustical environments. This paper describes a low-vocabulary speech recognition algorithm that provides robust performance in noisy environments with particular emphasis on characteristics due to the Lombard effect. A neutral and stressed-based source generator framework is established to achieve improved speech parameter characterization using a morphological constrained enhancement algorithm and stressed source compensation, which is unique for each source generator across a stressed speaking class. The algorithm uses a noise-adaptive boundary detector to obtain a sequence of source generator classes, which is used to direct noise parameter enhancement and stress compensation. This allows the parameter enhancement and stress compensation schemes to adapt to changing speech generator types. A phonetic consistency rule is also employed based on input source generator partitioning. Algorithm performance evaluation is demonstrated for noise-free and nine noisy Lombard speech conditions that include additive white Gaussian noise, slowly varying computer fan noise, and aircraft cockpit noise. System performance is compared with a traditional discrete-observation recognizer with no embellishments. Recognition rates are shown to increase from an average 36.7% for a baseline recognizer to 74.7% for the new algorithm (a 38% improvement). The new algorithm is also shown to be more consistent, as demonstrated by a decrease in standard deviation of recognition from 21.1 to 11.9 and a reduction in confusable word-pairs under noisy, Lombard-effect stressed speaking conditions