keyword-spotting

On-device wake word detection powered by deep learning

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

A lightweight, simple-to-use, RNN wake word listener

Deep learning for audio processing

💬 /so.nus/ STT (speech to text) for Node with offline hotword detection

ICASSP 2023-2024 Papers: A complete collection of influential and exciting research papers from the ICASSP 2023-24 conferences. Explore the latest advancements in acoustics, speech and signal processing. Code included. Star the repository to support the advancement of audio and signal processing!

This repository is a curated list of awesome Speech Keyword Spotting (Wake-Up Word Detection).

Code for Temporal Convolution for Real-time Keyword Spotting on Mobile Devices

Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus

wake word engine benchmark framework

Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769

[SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.

A lightweight, wake word detection engine. Train custom, high-accuracy models with minimal effort.

Deep Learning for Speech

Learning Efficient Representations for Keyword Spotting with Triplet Loss

In this repository, we explore using a hybrid system consisting of a Convolutional Neural Network and a Support Vector Machine for Keyword Spotting task.

Wav2Keyword is keyword spotting(KWS) based on Wav2Vec 2.0. This model shows state-of-the-art in Speech commands dataset V1 and V2.

Classify audio with neural nets on embedded systems like the Raspberry Pi

Offline wake word & keyword spotting engine. One ONNX model detects multiple keywords. ONNX/TFLite, model <130KB, inference <10ms. Runs on Android, ESP32, Linux, Web, and Home Assistant (Wyoming protocol server + HA add-on). No cloud, no data usage.