Efficient Isolated Speech to Sign Conversion Based on the Adaptive Rate Processing

This paper proposes a novel approach, based on the adaptive rate processing and analysis, of achieving a visual transformation of the isolated speech. The idea is to smartly combine the adaptive rate signal processing and classification for realizing an effective speech recognition and its transformation in sign. The incoming speech signal is digitized with an event-driven A/D converter (EDADC). The output of EDADC is windowed with an activity selection process. These windows are later on resampled uniformly with an adaptive rate interpolator. The resampled windows are de-noised with an adaptive rate filter and their spectrum are computed with an adaptive resolution short time Fourier transform (ARSTFT). Later on, the magnitude, Delta and Delta-Delta spectral coefficients are extracted. The K-Nearest Neighbor (KNN) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are the classification decisions. The classification decision is transformed into a systematic sign. The system functionality is tested for a case study and results are presented. A 7.9times reduction in acquired number of samples is achieved by the devised approach as compared to the classical one. It aptitudes a significant computational gain and power consumption reduction of the proposed system over the counter classical ones. An average subject dependent isolated speech recognition accuracy of 96.6% is achieved. It shows that the proposed approach can be employed in potential applications like industrial and noisy environments, integration of people with impaired hearing, etc.