Ensemble Hierarchical Extreme Learning Machine for Speech Dereverberation

Tassadaq Hussain, Sabato Marco Siniscalchi, Hsiao Lan Sharon Wang, Yu Tsao, Salerno Valerio Mario, Wen Hung Liao

Research output: Contribution to journalArticle

Abstract

Data-driven deep learning solutions, which are gradient-based neural architectures, have proven useful in overcoming some limitations of traditional signal processing techniques. However, a large number of reverberated-anechoic training utterance pairs covering as many environmental conditions as possible is required to achieve robust performance in unseen testing conditions. In this study, 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 reverberated one based on a spectral mapping. In addition to the ensemble learning framework, we further derive two novel HELM models, namely highway HELM, termed HELM(Hwy), and residual HELM, termed 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 TIMIT, MHINT, and REVERB corpora. 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.

Original languageEnglish
JournalIEEE Transactions on Cognitive and Developmental Systems
DOIs
Publication statusAccepted/In press - 2019 Jan 1

Keywords

  • Ensemble Learning
  • Hierarchical Extreme Learning Machines
  • Highway Extreme Learning Machine
  • Residual Extreme Learning Machine.
  • Speech Dereverberation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Ensemble Hierarchical Extreme Learning Machine for Speech Dereverberation'. Together they form a unique fingerprint.

  • Cite this