Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environment

environment List of unusual symbols used Number of pages: 26 Number of tables: 4 Number of figures: 1 List of Figures Fig. 1. Block diagram of the context-adaptive speech front-end with GMM-based clustering of the feature space in the first stage and mapping function for speech enhancement channel selection in the second stage. 22 List of Tables Table 1. Speech recognition performance (in terms of WRR) for different speech enhancement methods, for bi-gram and tri-gram language models. 23 Table 2. Number of speech utterances for which the specific speech enhancement method led to the highest word recognition rate (WRR). 24 Table 3. Accuracy of selecting the proper speech enhancement method (in percentages) for various implementations of the mapping function, for different size of the input vector V = 4, 12, 28, 60, and 124. 25 Table 4. Word recognition rates (in percentages) for various implementations of the mapping function, for different size of the input vector Abstract Based on the observation that dissimilar speech enhancement algorithms perform differently for different types of interference and noise conditions, we propose a context-adaptive speech pre-processing scheme, which performs adaptive selection of the most advantageous speech enhancement algorithm for each condition. The selection process is based on an unsupervised clustering of the acoustic feature space and a subsequent mapping function that identifies the most appropriate speech enhancement channel for each audio input, corresponding to unknown environmental conditions. Experiments performed on the MoveOn motorcycle speech and noise database validate the practical value of the proposed scheme for speech enhancement and demonstrate a significant improvement in terms of speech recognition accuracy, when compared to the one of the best performing individual speech enhancement algorithm. This is expressed as accuracy gain of 3.3% in terms of word recognition rate. The advance offered in the present work reaches beyond the specifics of the present application, and can be beneficial to spoken interfaces operating in fast-varying noise environments.