Picture for Daniel Galvez

Daniel Galvez

Label-Looping: Highly Efficient Decoding for Transducers

Add code
Jun 10, 2024
Viaarxiv icon

Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU

Add code
Jun 06, 2024
Viaarxiv icon

GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition

Add code
Nov 08, 2023
Viaarxiv icon

Speech Wikimedia: A 77 Language Multilingual Speech Dataset

Add code
Aug 30, 2023
Viaarxiv icon

LSH methods for data deduplication in a Wikipedia artificial dataset

Add code
Dec 10, 2021
Viaarxiv icon

The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage

Add code
Nov 17, 2021
Figure 1 for The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
Figure 2 for The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
Figure 3 for The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
Figure 4 for The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
Viaarxiv icon

Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio

Add code
Nov 21, 2017
Figure 1 for Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio
Figure 2 for Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio
Viaarxiv icon