A Robust Acoustic Feature Extraction Approach Based on Stacked Denoising Autoencoder

Liu, J.H.; Zheng, Weiqiao; Zou, Yuexian

doi:10.1109/bigmm.2015.46

Cited by 10 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of its success, a lot of effort has been made to improve the noise and duration robustness of the i-vector/PLDA framework in recent years. For example, attempts have been made to enhance and restore speech in the feature domain [5] using factor analysis and in the spectral domain [6,7] or ivector space [8,9] using denoising autoencoders (DAE) [10]. Improving noise robustness of PLDA models is another direction.…”

Section: Introductionmentioning

confidence: 99%

i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification

Tan

Mak

2017

Interspeech 2017

View full text Add to dashboard Cite

This paper proposes applying multi-task learning to train deep neural networks (DNNs) for calibrating the PLDA scores of speaker verification systems under noisy environments. To facilitate the DNNs to learn the main task (calibration), several auxiliary tasks were introduced, including the prediction of SNR and duration from i-vectors and classifying whether an i-vector pair belongs to the same speaker or not. The possibility of replacing the PLDA model by a DNN during the scoring stage is also explored. Evaluations on noise contaminated speech suggest that the auxiliary tasks are important for the DNNs to learn the main calibration task and that the uncalibrated PLDA scores are an essential input to the DNNs. Without this input, the DNNs can only predict the score shifts accurately, suggesting that the PLDA model is indispensable.

show abstract

Section: Introductionmentioning

confidence: 99%

i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification

Tan

Mak

2017

Interspeech 2017

View full text Add to dashboard Cite

show abstract

“…In our framework, other sizes of convolution kernels are also allowed. Moreover, the type of noise added is not limited to Gaussian noise, and other noise is also possible [63]. Further literature [64] proposed a classification approach called denoising and spare auto-encoder by combining DAE and SAE.…”

Section: Discussionmentioning

confidence: 99%

A Stacked Multi-Granularity Convolution Denoising Auto-Encoder

Cao

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

With the development of big data, artificial intelligence has provided many intelligent solutions to urban life. For instance, an image-based intelligent technology, such as image classification of diseases, is widely used in daily life. However, the image in real life is mostly unlabeled, so the performance of many image-based intelligent models shows limitations. Therefore, how to use a large amount of unlabeled image data to build an efficient and high-quality model for better urban life has been an urgent research topic. In this paper, we propose an unsupervised image feature extraction method that is referred to as a stacked multigranularity convolution denoising auto-encoder (SMGCDAE). The algorithm is based on a convolutional neural network (CNN), yet it introduces a multi-granularity kernel. This approach resolved issues with image unicity by extracting a diverse category of high-level features. In addition, the denoising auto-encoder ensures stability and improves the classification accuracy by extracting more robust features. The algorithm was assessed using three image benchmark datasets and a series of meningitis images, achieving higher average accuracy than other methods. These results suggest that the algorithm is capable of extracting more discriminative high-level features and thus offers superior performance compared with the existing methodologies.INDEX TERMS Unsupervised learning, feature extraction, denoising auto-encoder, convolutional neural network.

show abstract

“…The idea of SDAE is to stack multiple DAEs to form a new deep network structure. The specific number of stacked DAEs depends on the actual demand [18,19]. Each layer of the network can be regarded as a DAE, which is trained layer by layer through multiple iterations.…”

Section: Stacked Dae (Sdae)mentioning

confidence: 99%

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Guo,

Song,

Zeng

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

To improve pipeline transportation efficiency, long-distance pipelines need to be cleaned regularly. Pipeline inspection gauges (PIGs) are widely used in pigging operations. The traditional PIG localization method generally has a large error and cannot achieve continuous tracking. To solve the problem of PIG real-time tracking and localization, this paper proposes a method of PIG localization for oil pipelines based on a denoising autoencoder(DAE). The attention deconvolution residual block (ADR) is introduced in the decoder part of the DAE, so that this model can learn and use global information to selectively emphasize key features, suppress useless features, and improve the noise removal performance of the model. After denoising, the negative pressure wave(NPW) signal is normalized, the time delay is extracted, and the PIG is located using the NPW localization formula. Experiments show that this method can effectively achieve real-time PIG localization. Compared with the EMD and DAE positioning methods, the relative positioning accuracy is increased by 3.5 times and 8.4 times, respectively.

show abstract

A Robust Acoustic Feature Extraction Approach Based on Stacked Denoising Autoencoder

Cited by 10 publications

References 9 publications

i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification

i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification

A Stacked Multi-Granularity Convolution Denoising Auto-Encoder

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Contact Info

Product

Resources

About