Optimization of perceptually-based ASR front-end (automatic speech recognition)

Several recently proposed automatic speech recognition (ASR) front-ends are experimentally compared for speaker-dependent and cross-speaker ASR. The perceptually based linear predictive front-end yields the highest accuracies. By modifying its sensitivity to spectral peaks and to spectral tilt and by utilizing the speech dynamics the authors further improve, by about 10%, its error rate in speaker-independent ASR.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>