Keyword Spotting
95 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
Latest papers
What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions
There is increasing interest in the use of the LEArnable Front-end (LEAF) in a variety of speech processing systems.
Noise-Robust Keyword Spotting through Self-supervised Pretraining
aau-es-ml/ssl_noise-robust_kws
•
•
Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a good performance.
The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language
In this project, we demonstrate that phoneme-based models for speech processing can achieve strong crosslinguistic generalizability to unseen languages.
Cluster-based pruning techniques for audio data
boris-bergsma/audio_pruning
•
•
In this work, we introduce, for the first time in the context of the audio domain, the k-means clustering as a method for efficient data pruning.
Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models
DataSenseiAryan/GoogleSpeechCommandLowFootprint
•
•
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics 2023
In this work, we explore Quaternion neural models as an alternative for effective acoustic modeling for the KWS task.
PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords
This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance.
Keyword Spotting Simplified: A Segmentation-Free Approach using Character Counting and CTC re-scoring
Recent advances in segmentation-free keyword spotting treat this problem w. r. t.
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics
Keyword Spotting (KWS) models on embedded devices should adapt fast to new user-defined words without forgetting previous ones.
Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems
mrusci/ondevice-fewshot-kws
•
•
A personalized KeyWord Spotting (KWS) pipeline typically requires the training of a Deep Learning model on a large set of user-defined speech utterances, preventing fast customization directly applied on-device.
Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers
pulp-platform/pulp-trainlib
•
•
Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications.
