A Noise-Aware Memory-Attention Network Architecture for Regression-Based Speech Enhancement
We propose a novel noise-aware memory-attention network (NAMAN) for regression-based speech enhancement, aiming at improving quality of enhanced speech in unseen noise conditions. The NAMAN architecture consists of three parts, a main regression network, a memory block and an attention block. First, a long short-term memory recurrent neural network (LSTM-RNN) is adopted as the main network to well model the acoustic context of neighboring frames. Next, the memory block is built with an extensive set of noise feature vectors as the prior noise bases. Finally, the attention block serves as an auxiliary network to improve the noise awareness of the main network by encoding the dynamic noise information at frame level through additional features obtained by weighing the existing noise basis vectors in the memory block. Our experiments show that the proposed NAMAN framework is compact and outperforms the state-of-the-art dynamic noise-aware training approaches in low SNR conditions.
Code (0)
등록된 구현이 없습니다.
Tasks
regressionSpeech EnhancementSimilar Papers 제목 키워드 기반
Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
Real-world time series data exhibit non-stationary behavior, regime shifts, and temporally varying noise (heteroscedastic) that degrade the robustness of standard regression models. We introduce the Variability-Aware Rec…
CiMRAG: CiM-Aware Domain-Adaptive and Noise-Resilient Retrieval-Augmented Generation for Edge-Based LLMs
Personalized virtual assistants powered by large language models (LLMs) on edge devices are attracting growing attention, with Retrieval-Augmented Generation (RAG) emerging as a key method for personalization by retrievi…
NoiseFormer -- Noise Diffused Symmetric Attention Transformer
Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the …
Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression
Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical…
HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method to adapt large language models (LLMs) for downstream tasks. In this paper, we first propose to deploy the LoRA-finetuned LLMs on the hybri…