Audio Noise Filter using Cycle Consistent Adversarial Network - CycleGAN ANF

Nguyen, Nam Son; Li, Tengpeng; Zhang, Xiaoqian; Sheng, Bo; Wang, Teng; Wang, Jiayin

doi:10.1109/iccc47050.2019.9064433

Cited by 1 publication

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Audio: Since the audio modality is more prone to noise factors, robustness to non-stationary background noise in audio segments obtained are key for effective analysis. For maximum compatibility with our methodology we used a Cycle GAN based Audio Noise Filter [24] to carry out stationary/non-stationary noise cancellation from speech. The architecture of the same wasn't varied from the original version [24].…”

Section: Backend Modelmentioning

confidence: 99%

“…For maximum compatibility with our methodology we used a Cycle GAN based Audio Noise Filter [24] to carry out stationary/non-stationary noise cancellation from speech. The architecture of the same wasn't varied from the original version [24]. Filtered audio samples are used for feature extraction by a pre-build acoustic feature extraction application know as COVAREP [25].…”

Section: Backend Modelmentioning

confidence: 99%

See 1 more Smart Citation

Depression Status Estimation by Deep Learning based Hybrid Multi-Modal Fusion Model

Shalu,

et al. 2020

Preprint

View full text Add to dashboard Cite

Preliminary detection of mild depression could immensely help in effective treatment of the common mental health disorder. Due to the lack of proper awareness and the ample mix of stigmas and misconceptions present within the society, mental health status estimation has become a truly difficult task. Due to the immense variations in character level traits from person to person, traditional deep learning methods fail to generalize in a real world setting. In our study we aim to create a human allied AI workflow which could efficiently adapt to specific users and effectively perform in real world scenarios. We propose a Hybrid deep learning approach that combines the essence of one shot learning, classical supervised deep learning methods and human allied interactions for adaptation. In order to capture maximum information and make efficient diagnosis video,audio, and text modalities are utilized. Our Hybrid Fusion model achieved a high accuracy of 96.3% on the Dataset; and attained an AUC of 0.9682 which proves its robustness in discriminating classes in complex real-world scenarios making sure that no cases of mild depression are missed during diagnosis. The proposed method is deployed in a cloud based smartphone application for robust testing. With user specific adaptations and state of the art methodologies, we present a state-of-the-art model with user friendly experience.

show abstract

Section: Backend Modelmentioning

confidence: 99%