Voice Driven Applications in Non-stationary and Chaotic Environment

Automated operations based on voice commands will become more and more important in many applications, including robotics, maintenance operations, etc. However, voice command recognition rates drop quite a lot under non-stationary and chaotic noise environments. In this paper, we tried to significantly improve the speech recognition rates under non-stationary noise environments. First, 298 Navy acronyms have been selected for automatic speech recognition. Data sets were collected under 4 types of noisy environments: factory, buccaneer jet, babble noise in a canteen, and destroyer. Within each noisy environment, 4 levels (5 dB, 15 dB, 25 dB, and clean) of Signal-to-Noise Ratio (SNR) were introduced to corrupt the speech. Second, a new algorithm to estimate speech or no speech regions has been developed, implemented, and evaluated. Third, extensive simulations were carried out. It was found that the combination of the new algorithm, the proper selection of language model and a customized training of the speech recognizer based on clean speech yielded very high recognition rates, which are between 80% and 90% for the four different noisy conditions. Fourth, extensive comparative studies have also been carried out.

Investigations of Free-to-Roll Motions and its Active Control under Pitch-up Maneuvers

Experiments have been carried out at sub-critical Reynolds number to investigate free-to-roll motions induced by forebody and/or wings complex flow on a 30° swept back nonslender wings-slender body-model for static and dynamic (pitch-up) cases. For the dynamic (pitch-up) case it has been observed that roll amplitude decreases and lag increases with increase in pitching speed. Decrease in roll amplitude with increase in pitch rate is attributed to low disturbing rolling moment due to weaker interaction between forebody and wing flow components. Asymmetric forebody vortices dominate and control the roll motion of the model in dynamic case when non-dimensional pitch rate ≥ 1x10-2. Effectiveness of the active control scheme utilizing rotating nose with artificial tip perturbation is observed to be low in the angle of attack region where the complex flow over the wings has contributions from both forebody and wings.

Continuous Feature Adaptation for Non-Native Speech Recognition

The current speech interfaces in many military applications may be adequate for native speakers. However, the recognition rate drops quite a lot for non-native speakers (people with foreign accents). This is mainly because the nonnative speakers have large temporal and intra-phoneme variations when they pronounce the same words. This problem is also complicated by the presence of large environmental noise such as tank noise, helicopter noise, etc. In this paper, we proposed a novel continuous acoustic feature adaptation algorithm for on-line accent and environmental adaptation. Implemented by incremental singular value decomposition (SVD), the algorithm captures local acoustic variation and runs in real-time. This feature-based adaptation method is then integrated with conventional model-based maximum likelihood linear regression (MLLR) algorithm. Extensive experiments have been performed on the NATO non-native speech corpus with baseline acoustic model trained on native American English. The proposed feature-based adaptation algorithm improved the average recognition accuracy by 15%, while the MLLR model based adaptation achieved 11% improvement. The corresponding word error rate (WER) reduction was 25.8% and 2.73%, as compared to that without adaptation. The combined adaptation achieved overall recognition accuracy improvement of 29.5%, and WER reduction of 31.8%, as compared to that without adaptation.