MLPerf Tiny Benchmark

mlcommons/tiny • • 14 Jun 2021

Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications.

SSAST: Self-Supervised Audio Spectrogram Transformer

YuanGongND/ssast • • 19 Oct 2021

However, pure Transformer models tend to require more training data compared to CNNs, and the success of the AST relies on supervised pretraining that requires a large amount of labeled data and a complex training pipeline, thus limiting the practical usage of AST.

Progressive Continual Learning for Spoken Keyword Spotting

huangyz0918/kws-continual-learning • • 29 Jan 2022

Catastrophic forgetting is a thorny challenge when updating keyword spotting (KWS) models after deployment.

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit

PaddlePaddle/PaddleSpeech • • NAACL (ACL) 2022

PaddleSpeech is an open-source all-in-one speech toolkit.

Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining

holgerbovbjerg/data2vec-kws • • 4 Oct 2022

This paper explores the effectiveness of SSL on small models for KWS and establishes that SSL can enhance the performance of small KWS models when labelled data is scarce.

What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision

malmaud/whats_cookin • 5 Mar 2015

We present a novel method for aligning a sequence of instructions to a video of someone carrying out a task.

What’s Cookin’? Interpreting Cooking Videos using Text, Speech and Vision

malmaud/whats_cookin • HLT 2015

GTM-UVigo Systems for the Query-by-Example Search on Speech Task at MediaEval 2015

gtm-uvigo/MediaEval_QUESST2015 • MediaEval 2015 Workshop 2015

In this paper, we present the systems developed by GTMUVigo team for the query by example search on speech task (QUESST) at MediaEval 2015.

Zero-shot keyword spotting for visual speech recognition in-the-wild

lilianemomeni/KWS-Net • • ECCV 2018

Visual keyword spotting (KWS) is the problem of estimating whether a text query occurs in a given recording using only video information.

Federated Learning for Keyword Spotting

snipsco/keyword-spotting-research-datasets • 9 Oct 2018

We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors.