2018 · 15 citations · 15 references
Health ProfessionsLinguisticsAcousticsPhoneticsPsychoacousticsNoise ReductionSpeech AcousticsSpeech Intelligibility EnhancementSpeech RecognitionLong Short-term Memory NetworksNoise Robust Speech AnalysisRecurrent Neural NetworksSignal-to-noise Ratio ImprovementSpeech EnhancementSpeech Enhancement AlgorithmsSpeech Quality AssessmentSpeech Signal Enhancement
Body-conducted microphone (BCM) speech is immune to noise but has the shortcomings such as severe loss of high-frequency components. Direct enhancement about BCM speech is meaningful but few works have been done so far. Firstly, considering the lack of open datasets, a specific dataset of throat microphone (TM) speech is constructed by us and now is opened online. Secondly, we propose a novel speaker-dependent TM speech enhancement framework based on deep bidirectional recurrent neural networks using Long Short-Term Memory units (BLSTM-RNN). In this framework, magnitude spectrums are directly transformed to achieve speech enhancement, which is different from previous works based on the source-filter model. BLSTM-RNN is deployed to further improve the results of transformation. Objective and subjective results show that the quality of TM speech is substantially improved, where PESQ, STOI and MOS scores are improved 0.71, 0.21 and 1.36 respectively. Another important criterion, LSD decreases 0.63. Another important criterion, LSD decreases 0.63.
15
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
An Experimental Study on Speech Enhancement Based on Deep Neural Networks
Yong Xu, Jun Du, Li-Rong Dai et al. · IEEE Signal Processing Letters · 2013 · 952 citations