Search Results for author: Pete Warden

Found 8 papers, 6 papers with code

Few-Shot Keyword Spotting in Any Language

1 code implementation3 Apr 2021 Mark Mazumder, Colby Banbury, Josh Meyer, Pete Warden, Vijay Janapa Reddi

With just five training examples, we fine-tune the embedding model for keyword spotting and achieve an average F1 score of 0. 75 on keyword classification for 180 new keywords unseen by the embedding model in these nine languages.

Keyword Spotting Transfer Learning

Data Engineering for Everyone

no code implementations23 Feb 2021 Vijay Janapa Reddi, Greg Diamos, Pete Warden, Peter Mattson, David Kanter

This article shows that open-source data sets are the rocket fuel for research and innovation at even some of the largest AI organizations.

TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems

1 code implementation17 Oct 2020 Robert David, Jared Duke, Advait Jain, Vijay Janapa Reddi, Nat Jeffries, Jian Li, Nick Kreeger, Ian Nappier, Meghna Natraj, Shlomi Regev, Rocky Rhodes, Tiezhen Wang, Pete Warden

We introduce TensorFlow Lite Micro (TF Micro), an open-source ML inference framework for running deep-learning models on embedded systems.

Visual Wake Words Dataset

3 code implementations12 Jun 2019 Aakanksha Chowdhery, Pete Warden, Jonathon Shlens, Andrew Howard, Rocky Rhodes

To facilitate the development of microcontroller friendly models, we present a new dataset, Visual Wake Words, that represents a common microcontroller vision use-case of identifying whether a person is present in the image or not, and provides a realistic benchmark for tiny vision models.

Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition

18 code implementations9 Apr 2018 Pete Warden

Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems.

Accuracy Metrics automatic-speech-recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.