Posts by Justin Luitjens
Technical Walkthrough
Aug 20, 2020
Extracting Features from Multiple Audio Channels with Kaldi
In automatic speech recognition (ASR), one widely used method combines traditional machine learning with deep learning. In ASR flows of this type…
13 MIN READ
Technical Walkthrough
Oct 17, 2019
GPU-Accelerated Speech to Text with Kaldi: A Tutorial on Getting Started
Recently, NVIDIA achieved GPU-accelerated speech-to-text inference with exciting performance results. That blog post described the general process of the Kaldi…
12 MIN READ
Technical Walkthrough
Mar 18, 2019
NVIDIA Accelerates Real Time Speech to Text Transcription 3500x with Kaldi
NVIDIA tested chieved speech-to-text inferencingachieving speech-to-text inferencing 3,524x faster than real-time processing using an NVIDIA Tesla V100.
8 MIN READ
Technical Walkthrough
Sep 04, 2014
CUDA Pro Tip: Always Set the Current Device to Avoid Multithreading Bugs
A simple rule to avoid multithreading bugs in applications that run in parallel on multiple GPUs.
3 MIN READ
Technical Walkthrough
Feb 13, 2014
Faster Parallel Reductions on Kepler
Parallel reduction is a common building block for many parallel algorithms. A presentation from 2007 by Mark Harris provided a detailed strategy for…
12 MIN READ
Technical Walkthrough
Dec 04, 2013
CUDA Pro Tip: Increase Performance with Vectorized Memory Access
This post demonstrates the use of vectorized memory access in CUDA C/C++ to increase bandwidth utilization while decreasing instruction count.
6 MIN READ
