用于关键词识别的多锥形梅尔频谱图

Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting

In the context of keyword spotting (KWS), the replacement of handcrafted speech features by learnable features has not yielded superior KWS performance. In this study, we demonstrate that filterbank learning outperforms handcrafted speech features for KWS whenever the number of filterbank channels is severely decreased. Reducing the number of channels might yield certain KWS performance drop, but also a substantial energy consumption reduction, which is key when deploying common always-on KWS on low-resource devices. Experimental results on a noisy version of the Google Speech Commands Dataset…

End-to-end Keyword Spotting using Neural Architecture Search and Quantization

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms. After a suitable KWS model is found with NAS, we conduct quantization of weights and activations to reduce the memory footprint. We conduct extensive experiments on the Google speech commands dataset. In particular, we compare our end-to-end approach to mel-frequency cepstral coefficient (MFCC) bas…

A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting

Robustness against noise is critical for keyword spotting (KWS) in real-world environments. To improve the robustness, a speech enhancement front-end is involved. Instead of treating the speech enhancement as a separated preprocessing before the KWS system, in this study, a pre-trained speech enhancement front-end and a convolutional neural networks (CNNs) based KWS system are concatenated, where a feature transformation block is used to transform the output from the enhancement front-end into the KWS system's input. The whole model is trained jointly, thus the linguistic and other useful info…

关键词唤醒——利用深度学习检测语音中的指令

Keyword spotting -- Detecting commands in speech using deep learning

本文研究语音关键词唤醒，通过MFCC特征工程比较HMM、CNN及带注意力的RNN等模型，发现BiLSTM加Attention的RNN效果最佳，准确率达93.9%。

使用移位增量系数的端到端用户自定义关键词识别

End-to-End User-Defined Keyword Spotting using Shifted Delta Coefficients

针对用户自定义关键词识别中相近发音区分难的问题，提出采用移位增量系数（SDC）结合交叉注意力端到端系统，在Libriphrase-hard数据集上较MFCC基线提升AUC 8.32%、EER 8.69%，优于现有技术。

TsetlinKWS：一款用于关键词识别的65nm 16.58μW、0.63mm²基于状态驱动卷积Tsetlin机的加速器

TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting

针对Tsetlin机在语音任务性能有限的问题，提出首个CTM关键词识别算法-硬件协同设计框架TsetlinKWS，通过新型特征提取、模型压缩与状态驱动架构实现高精度与超低功耗，为语音应用提供高效方案。