Switching linear dynamic transducer for stereo data based speech feature mapping

The performance of a speech recognition system may be degraded even without any background noise because of the linear or non-linear distortions incurred by recording devices or reverberations. One of the well-known approaches to reduce this channel distortion is feature mapping which maps the distorted speech feature to its clean counterpart. The feature mapping rule is usually trained based on a set of stereo data which consists of the simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to speech feature sequence mapping based on the switching linear dynamic transducer (SLDT). The proposed algorithm enables us a sequence-to-sequence mapping in a systematic way, instead of the traditional vectorto-vector mapping. The proposed approach is applied to compensate channel distortion in speech recognition and shows improvement in recognition performance.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Chang Woo Han, Tae Gyoon Kang, Doo Hwa Hong, Nam Soo Kim, Kiwan Eom, Jaewon Lee
• Keywords: Channel Distortion, Feature Mapping, ICASSP 2011, Signal Processing, Speech Recognition