DNN-Based Feature Enhancement Using DOA-Constrained ICA for Robust Speech Recognition

Lee, Ho-Yong; Cho, Ji-Won; Kim, Minook; Park, Hyung‐Min

doi:10.1109/lsp.2016.2583658

Cited by 30 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, since the new computational and performance advances brought by the recent developments in the field of deep neural networks (DNNs) research, their use is now being investigated in a variety of acoustic and speech oriented applications involving multichannel processing, including in a few cases the specific problem of acoustic source localization. To date, the application of DNNs to multichannel processing problems has focused principally on ASR [28], [48], speech enhancement [49], acoustic source separation [50], and acoustic source localization [51]. In [28], a DNN-based feature enhancement method using multichannel inputs is proposed for robust ASR.…”

Section: B Machine Learning Methods For Multichannel Processingmentioning

confidence: 99%

“…To date, the application of DNNs to multichannel processing problems has focused principally on ASR [28], [48], speech enhancement [49], acoustic source separation [50], and acoustic source localization [51]. In [28], a DNN-based feature enhancement method using multichannel inputs is proposed for robust ASR. The multichannel information is used in the pre-enhanced spectral features that are obtained by DOA-constrained independent component analysis.…”

Section: B Machine Learning Methods For Multichannel Processingmentioning

confidence: 99%

“…Applications of this scenario include videoconferencing systems [27], in which the estimation of sound coordinates can be used to automatically steer a videocamera towards an active speaker; human-computer interaction systems [28], in which localization and beamforming are used to enhance the signal and improve audio recognition; or even multimedia interactive systems for performing arts, in which acoustic source localization can be integrated into digital musical interfaces and used for performance control [29]. The method can be extended in principle to a multiple-source scenario, which would require to improve the routine devoted to peak searching in the acoustic response power.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting CNNs for Improving Acoustic Source Localization in Noisy and Reverberant Conditions

Salvati

Drioli

Foresti

2018

IEEE Trans. Emerg. Top. Comput. Intell.

View full text Add to dashboard Cite

The paper discusses the application of convolutional neural networks (CNNs) to minimum variance distortionless response (MVDR) localization schemes. We investigate the direction of arrival (DOA) estimation problem in noisy and reverberant conditions using an uniform linear array (ULA). CNNs are used to process the multichannel data from the ULA and to improve the data fusion scheme which is performed in the steered response power (SRP) computation. CNNs improve the incoherent frequency fusion of the narrowband response power by weighting the components, reducing the deleterious effects of those components affected by artifacts due to noise and reverberation. The use of CNNs avoids the necessity of previously encoding the multichannel data into selected acoustic cues with the advantage to exploit its ability in recognizing geometrical pattern similarity. Experiments with both simulated and real acoustic data demonstrate the superior localization performance of the proposed SRP beamformer with respect to other state-ofthe-art techniques.

show abstract

Section: B Machine Learning Methods For Multichannel Processingmentioning

confidence: 99%

Section: B Machine Learning Methods For Multichannel Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting CNNs for Improving Acoustic Source Localization in Noisy and Reverberant Conditions

Salvati

Drioli

Foresti

2018

IEEE Trans. Emerg. Top. Comput. Intell.

View full text Add to dashboard Cite

show abstract

“…A novel joint training framework for speech separation and recognition [58] was provided to build a larger neural network, which jointly adjusts the weights in each model by concatenating a DNN-based speech separation frontend with more noise and reverberation. In order to reconstruct noise-robust features in various noise conditions, the authors of [59] applied DNN-based speech feature enhancement (FE) using a direction-of-arrival (DOA)-constrained independent component analysis (DCICA) to obtain multichannel input signals. To solve sensitivity to the recording conditions caused by a high level of background noise, the authors of [39] provided an adapting DNN-based acoustic using an audio database recorded by wireless sensors to train an accurate model for the actual speech processing application.…”

Section: A Classification Of Articles Based On Domain Problemsmentioning

confidence: 99%

Automatic Speech Recognition: Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

A huge amount of research has been done in the field of speech signal processing in recent years. In particular, there has been increasing interest in the automatic speech recognition (ASR) technology field. ASR began with simple systems that responded to a limited number of sounds and has evolved into sophisticated systems that respond fluently to natural language. This systematic review of automatic speech recognition is provided to help other researchers with the most significant topics published in the last six years. This research will also help in identifying recent major ASR challenges in real-world environments. In addition, it discusses current research gaps in ASR. This review covers articles available in five research databases that were completed according to the preferred reporting items for systematic reviews and metaanalyses (PRISMA) protocol. The search strategy yielded 45 articles related to the study's scope for the period 2015-2020. The results presented in this review shed light on research trends in the area of ASR and also suggest new research directions.

show abstract

“…Por exemplo, Bayesian feature enhancement (BFE) [174] que é um método que melhora de forma eficiente os atributos de voz corrompidos por ruído aditivo ou reverberação nos logarithmic mel-frequency power spectral LMPS, sendo considerado um pré-processamento eficiente para os sistemas RAV robusto com menos nós na rede.…”

Section: Técnicas De Compensação De Modelosunclassified

Realce E Reconhecimento De Voz Contínua Em Ambientes Adversos

GORDILLO¹

View full text Add to dashboard Cite

DNN-Based Feature Enhancement Using DOA-Constrained ICA for Robust Speech Recognition

Cited by 30 publications

References 23 publications

Exploiting CNNs for Improving Acoustic Source Localization in Noisy and Reverberant Conditions

Exploiting CNNs for Improving Acoustic Source Localization in Noisy and Reverberant Conditions

Automatic Speech Recognition: Systematic Literature Review

Realce E Reconhecimento De Voz Contínua Em Ambientes Adversos

Contact Info

Product

Resources

About