Ensemble Hierarchical Extreme Learning Machine for Speech Dereverberation

摘要

Data-driven deep learning solutions with gradient-based neural architecture, have proven useful in overcoming some limitations of traditional signal processing techniques. However, a large number of reverberant-anechoic training utterance pairs covering as many environmental conditions as possible is required to achieve robust dereverberation performance in unseen testing conditions. In this article, we propose to address the data requirement issue while preserving the advantages of deep neural structures leveraging upon hierarchical extreme learning machines (HELMs), which are not gradient-based neural architectures. In particular, an ensemble HELM learning framework is established to effectively recover anechoic speech from a reverberant one based on spectral mapping. In addition to the ensemble learning framework, we further derive two novel HELM models, namely, highway HELM [HELM(Hwy)] and residual HELM [HELM(Res)], both incorporating low-level features to enrich the information for spectral mapping. We evaluated the proposed ensemble learning framework using simulated and measured impulse responses by employing Texas Instrument and Massachusetts Institute of Technology (TIMIT), Mandarin hearing in noise test (MHINT), and reverberant voice enhancement and recognition benchmark (REVERB) corpora. The experimental results show that the proposed framework outperforms both traditional methods and a recently proposed integrated deep and ensemble learning algorithm in terms of standardized objective and subjective evaluations under matched and mismatched testing conditions for simulated and measured impulse responses.