Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks
원문 초록
Brain-inspired spiking neural networks (SNNs) have demonstrated great potential for temporal signal processing. However, their performance in speech processing remains limited due to the lack of an effective auditory front-end. To address this limitation, we introduce Spiking-LEAF, a learnable auditory front-end meticulously designed for SNN-based speech processing. Spiking-LEAF combines a learnable filter bank with a novel two-compartment spiking neuron model called IHC-LIF. The IHC-LIF neurons draw inspiration from the structure of inner hair cells (IHC) and they leverage segregated dendritic and somatic compartments to effectively capture multi-scale temporal dynamics of speech signals. Additionally, the IHC-LIF neurons incorporate the lateral feedback mechanism along with spike regularization loss to enhance spike encoding efficiency. On keyword spotting and speaker identification tasks, the proposed Spiking-LEAF outperforms both SOTA spiking auditory front-ends and conventional real-valued acoustic features in terms of classification accuracy, noise robustness, and encoding efficiency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model
Unsupervised Speech Representation Pooling Using Vector Quantization
ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification
Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
토론
이 논문과 연결된 포럼 글이 아직 없습니다.