Transfer Learning-based Deep Residual Learning For Speech Recognition In Clean And Noisy Environments

Abstract

Addressing the detrimental impact of non-stationary environmental noise on automatic speech recognition (ASR) has been a persistent and significant research focus. Despite advancements, this challenge continues to be a major concern. Recently, data-driven supervised approaches, such as deep neural networks, have emerged as promising alternatives to traditional unsupervised methods. With extensive training, these approaches have the potential to overcome the challenges posed by diverse real-life acoustic environments. In this light, this paper introduces a novel neural framework that incorporates a robust frontend into ASR systems in both clean and noisy environments. Utilizing the Aurora-2 speech database, the authors evaluate the effectiveness of an acoustic feature set for Mel-frequency, employing the approach of transfer learning based on Residual neural network (ResNet). The experimental results demonstrate a significant improvement in recognition accuracy compared to convolutional

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keydjeffal2025transfer

Related papers

• Deep Speech Enhancement For Reverberated And Noisy Signals Using Wide Residual Networks (2019)0.00
• Boosting Noise Robustness Of Acoustic Model Via Deep Adversarial Training (2018)9.23
• Towards Decoupling Frontend Enhancement And Backend Recognition In Monaural Robust ASR (2024)4.52
• Automatic Speech Recognition Using Advanced Deep Learning Approaches: A Survey (2024)16.63
• Improving Noise Robust Automatic Speech Recognition With Single-channel Time-domain Enhancement Network (2020)13.88
• Very Deep Convolutional Neural Networks For Robust Speech Recognition (2016)12.40
• A Network Of Deep Neural Networks For Distant Speech Recognition (2017)10.35
• Deep Learning For Distant Speech Recognition (2017)0.00