A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks

Wu, Bo; Li, Kehuang; Yang, Minglei; Lee, Chin‐Hui

doi:10.1109/taslp.2016.2623559

Cited by 85 publications

(67 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research for analysis, it needs normalization data for training process the GSI forecasting 60 min ahead, as defined [31], which can be calculated by Equation (18) …”

Section: Normalizationmentioning

confidence: 99%

“…In this research for analysis, it needs normalization data for training process the GSI forecasting 60 min ahead, as defined [31], which can be calculated by Equation (18): Let us denote GSI n dnorm and GSI n d be normalized target feature at frame index n and the d-GSI output, respectively. Let us also denote GSI max and GSI min be the maximum value and minimum values of the GSI, respectively.…”

Section: Normalizationmentioning

confidence: 99%

See 1 more Smart Citation

k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data

Chen

Kartini

2017

Energies

View full text Add to dashboard Cite

This paper proposes a novel methodology for very short term forecasting of hourly global solar irradiance (GSI). The proposed methodology is based on meteorology data, especially for optimizing the operation of power generating electricity from photovoltaic (PV) energy. This methodology is a combination of k-nearest neighbor (k-NN) algorithm modelling and artificial neural network (ANN) model. The k-NN-ANN method is designed to forecast GSI for 60 min ahead based on meteorology data for the target PV station which position is surrounded by eight other adjacent PV stations. The novelty of this method is taking into account the meteorology data. A set of GSI measurement samples was available from the PV station in Taiwan which is used as test data. The first method implements k-NN as a preprocessing technique prior to ANN method. The error statistical indicators of k-NN-ANN model the mean absolute bias error (MABE) is 42 W/m 2 and the root-mean-square error (RMSE) is 242 W/m 2 . The models forecasts are then compared to measured data and simulation results indicate that the k-NN-ANN-based model presented in this research can calculate hourly GSI with satisfactory accuracy.

show abstract

“…In this research for analysis, it needs normalization data for training process the GSI forecasting 60 min ahead, as defined [31], which can be calculated by Equation (18) …”

Section: Normalizationmentioning

confidence: 99%

Section: Normalizationmentioning

confidence: 99%

k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data

Chen

Kartini

2017

Energies

View full text Add to dashboard Cite

show abstract

“…In a single-channel case [12], we found that RT60-dependent frame shift and acoustic context are two key environment-aware parameters in DNN training, which can boost the system's environment robustness. While in multichannel case, we pay more attention to spatial information rather than frame shift, because spatial information captured by microphone array is fundamentally important to speech enhancement of speech acquisition in noisy environment.…”

Section: Introductionmentioning

confidence: 94%

“…In [10,11], a DNNbased single-microphone dereverberation system was proposed by adopting a sigmoid activation function at the output layer and min-max normalization of target features. An improved DNN dereverberation system we proposed recently [12] adopted a linear output layer and globally normalized the target features into zero mean and unit variance, achieving the state-of-the-art performances.…”

Section: Introductionmentioning

confidence: 99%

“…Different from beamforming, where expert knowledge has to be involved in order to reach the desired result, the DNN will eventually boost the signal in the direction of the desired source, and/or possibly ignore/deemphasize some of the available channels using information available in the data. To better assess the strength of the proposed approach, we also build two standard DNN-based dereverberation systems, namely DSB-DNN and DNNs-DSB, which are direct extensions of the single-microphone case in [12] by combining a beamformer with single or multiple DNN dereverberation systems. The experimental evidence confirms that the proposed DNNSpatial approach outperforms the other two more common DNN-based solutions investigated in this work, in both 2-microphone and 6-microphone settings, according to all of the three objective measures tested.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

Yang

Huang

et al. 2017

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

A reverberation-time-aware deep-neural-network (DNN)-based multi-channel speech dereverberation framework is proposed to handle a wide range of reverberation times (RT60s). There are three key steps in designing a robust system. First, to accomplish simultaneous speech dereverberation and beamforming, we propose a framework, namely DNNSpatial, by selectively concatenating log-power spectral (LPS) input features of reverberant speech from multiple microphones in an array and map them into the expected output LPS features of anechoic reference speech based on a single deep neural network (DNN). Next, the temporal auto-correlation function of received signals at different RT60s is investigated to show that RT60-dependent temporal-spatial contexts in feature selection are needed in the DNNSpatial training stage in order to optimize the system performance in diverse reverberant environments. Finally, the RT60 is estimated to select the proper temporal and spatial contexts before feeding the log-power spectrum features to the trained DNNs for speech dereverberation. The experimental evidence gathered in this study indicates that the proposed framework outperforms the state-of-the-art signal processing dereverberation algorithm weighted prediction error (WPE) and conventional DNNSpatial systems without taking the reverberation time into account, even for extremely weak and severe reverberant conditions. The proposed technique generalizes well to unseen room size, array geometry and loudspeaker position, and is robust to reverberation time estimation error.

show abstract

A context aware-based deep neural network approach for simultaneous speech denoising and dereverberation

Routray

Mao

2022

Neural Comput & Applic

View full text Add to dashboard Cite

A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks

Cited by 85 publications

References 29 publications

k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data

k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data

A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation

A context aware-based deep neural network approach for simultaneous speech denoising and dereverberation

Contact Info

Product

Resources

About