Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) For Speech Feature Enhancement

Abstract

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of denoising autoencoder (DAE). The proposed method uses skip connections in both encoder and decoder sides by passing speech information of the target frame from input to the model. It also uses a new objective function in training model that uses a correlation distance measure in penalty terms by measuring dependency of the latent target features and the model (latent features and enhanced features obtained from the DAE). Performance of the proposed method was compared against a conventional model and a state of the art model under both seen and unseen noisy environments of 7 different types of background noise with different SNR levels (0, 5, 10 and 20 dB). The proposed method also is teste

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keybadi2019correlation

Related papers

• Improved Far-field Speech Recognition Using Joint Variational Autoencoder (2022)0.00
• Analysis Of DNN Speech Signal Enhancement For Robust Speaker Recognition (2018)11.39
• On The Use Of DNN Autoencoder For Robust Speaker Recognition (2018)0.00
• End-to-end Recurrent Denoising Autoencoder Embeddings For Speaker Identification (2020)6.34
• DENT-DDSP: Data-efficient Noisy Speech Generator Using Differentiable Digital Signal Processors For Explicit Distortion Modelling And Noise-robust Speech Recognition (2022)0.00
• I-DCCRN-VAE: An Improved Deep Representation Learning Framework For Complex Vae-based Single-channel Speech Enhancement (2025)0.00
• Speaker Reinforcement Using Target Source Extraction For Robust Automatic Speech Recognition (2022)7.50
• Spatial-dccrn: Dccrn Equipped With Frame-level Angle Feature And Hybrid Filtering For Multi-channel Speech Enhancement (2022)5.84