Optimizing Neural Architectures for Hindi Speech Separation and Enhancement in Noisy Environments
This addresses speech processing for Hindi speakers in noisy environments, with a focus on edge devices, but is incremental as it builds on existing DEMUCS architecture.
This paper tackled Hindi speech separation and enhancement in noisy environments by refining the DEMUCS model with U-Net and LSTM layers, achieving superior performance in PESQ and STOI metrics, especially under extreme noise conditions.
This paper addresses the challenges of Hindi speech separation and enhancement using advanced neural network architectures, with a focus on edge devices. We propose a refined approach leveraging the DEMUCS model to overcome limitations of traditional methods, achieving substantial improvements in speech clarity and intelligibility. The model is fine-tuned with U-Net and LSTM layers, trained on a dataset of 400,000 Hindi speech clips augmented with ESC-50 and MS-SNSD for diverse acoustic environments. Evaluation using PESQ and STOI metrics shows superior performance, particularly under extreme noise conditions. To ensure deployment on resource-constrained devices like TWS earbuds, we explore quantization techniques to reduce computational requirements. This research highlights the effectiveness of customized AI algorithms for speech processing in Indian contexts and suggests future directions for optimizing edge-based architectures.