Keyword Spotting
96 papers with code • 10 benchmarks • 8 datasets
In speech processing, keyword spotting deals with the identification of keywords in utterances.
( Image credit: Simon Grest )
Benchmarks
These leaderboards are used to track progress in Keyword Spotting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Keyword Spotting models and implementationsDatasets
Speech Commands
TAU Urban Acoustic Scenes 2019
VoxForge
PodcastFillers
EmoSpeech
Most implemented papers
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
retrocirce/hts-audio-transformer
•
•
Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems.
Hello Edge: Keyword Spotting on Microcontrollers
ARM-software/ML-KWS-for-MCU
•
•
We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements.
Keyword Transformer: A Self-Attention Model for Keyword Spotting
ARM-software/keyword-transformer
•
•
The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition.
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning
•
•
We present a large-scale comparison of various self-supervised models.
Low-Power Audio Keyword Spotting using Tsetlin Machines
In this paper we explore a TM based keyword spotting (KWS) pipeline to demonstrate low complexity with faster rate of convergence compared to NNs.
READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents
Well established text line segmentation evaluation schemes such as the Detection Rate or Recognition Accuracy demand for binarized data that is annotated on a pixel level.
Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting
castorini/honk
•
•
We describe Honk, an open-source PyTorch reimplementation of convolutional neural networks for keyword spotting that are included as examples in TensorFlow.
Deep Residual Learning for Small-Footprint Keyword Spotting
castorini/honk
•
•
We explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark.
Efficient keyword spotting using dilated convolutions and gating
snipsco/tract
•
•
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states.
AST: Audio Spectrogram Transformer
YuanGongND/ast
•
•
In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels.
