Optimization of a speech recognizer for aircraft environments
نویسندگان
چکیده
Speech recognition in aircrafts can greatly simplify operation of equipment in both military and civil environments. This paper describes the development of specialized recognizers for two military applications: One for assisting a jet pilot wearing a breathing mask and another for a radar evaluator within an aircraft (similarly to AWACS). In both cases it is not practical to collect su cient speech data under real conditions for a robust specialized recognizer. This paper describes two methods for overcoming this data problem and building a recognizer with minimal e ort: retraining the baseline system with real application data and combining the baseline system with a new trained system. These methods greatly improved the performance of the baseline system (US English recognizer adapted to car environment).
منابع مشابه
Subband parameter optimization of microphone arrays for speech recognition in reverberant environments
In this paper, we present a new subband microphone array processing algorithm specifically designed for speech recognition applications. We previously proposed a speech recognizer-based array processing algorithm which resulted in significant improvements in recognition accuracy when the speech was corrupted by additive noise and moderate levels of reverberation. However, little improvement was...
متن کاملMorphological 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 aod stress...
متن کاملمدل میکروسکوپی دوگوشی مبتنی بر فیلتر بانک مدولاسیون برای پیش گویی قابلیت فهم گفتار در افراد دارای شنوایی عادی
In this study, a binaural microscopic model for the prediction of speech intelligibility based on the modulation filter bank is introduced. So far, the spectral criteria such as the STI and SII or other analytical methods have been used in the binaural models to determine the binaural intelligibility. In the proposed model, unlike all models of binaural intelligibility prediction, an automatic ...
متن کاملMorphological Constrained Feature Enhancement with Adaptive Cepstral Compensation (mce-acc) for Speech Recognition in Noise and Lombard Eeect
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 which provides robust performance in noisy environments with particular emphasis on characteristics due to Lombard eeect. A neutral and stressed b...
متن کاملDistribution Systems Reconfiguration Using Pattern Recognizer Neural Networks
A novel intelligent neural optimizer with two objective functions is designed for electrical distribution systems. The presented method is faster than alternative optimization methods and is comparable with the most powerful and precise ones. This optimizer is much smaller than similar neural systems. In this work, two intelligent estimators are designed, a load flow program is coded, and a spe...
متن کامل