Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Keyword SpottingSpeaker IdentificationSimilar Papers 제목 키워드 기반
EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use
In audio classification, differentiable auditory filterbanks with few parameters cover the middle ground between hard-coded spectrograms and raw audio. LEAF (arXiv:2101.08596), a Gabor-based filterbank combined with Per-…
Audio ClassificationClassificationInstrument RecognitionPitch Classification+1An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks
Auditory front-end is an integral part of a spiking neural network (SNN) when performing auditory cognitive tasks. It encodes the temporal dynamic stimulus, such as speech and audio, into an efficient, effective and reco…
Benchmarkingspeech-recognitionSpeech RecognitionsVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks
Speech applications are expected to be low-power and robust under noisy conditions. An effective Voice Activity Detection (VAD) front-end lowers the computational need. Spiking Neural Networks (SNNs) are known to be biol…
Action DetectionActivity DetectionDigit Recognition using Multimodal Spiking Neural Networks
Spiking neural networks (SNNs) are the third generation of neural networks that are biologically inspired to process data in a fashion that emulates the exchange of signals in the brain. Within the Computer Vision commun…
Impact of spiking neurons leakages and network recurrences on event-based spatio-temporal pattern recognition
Spiking neural networks coupled with neuromorphic hardware and event-based sensors are getting increased interest for low-latency and low-power inference at the edge. However, multiple spiking neuron models have been pro…