SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC On-Demand

AI Application Deployment and Inference
Presentation
Media
Accelerate Your Kaldi Speech Pipeline on the GPU
Voice commands, and advancements in automatic speech recognition algorithms, that help us interact conversationally with devices, appliances and services, are growing within our everyday environment. We will share some highlights and results from work scheduling optimizations in the Kaldi framework. The first part of the talk will describe results focused primarily on optimizing the DNN components of speech pipeline. We will then show results from a GPU optimized fast lattice decode algorithm to achieve high end to end throughput across the whole ASR pipeline from the acoustic model to the language model.
Voice commands, and advancements in automatic speech recognition algorithms, that help us interact conversationally with devices, appliances and services, are growing within our everyday environment. We will share some highlights and results from work scheduling optimizations in the Kaldi framework. The first part of the talk will describe results focused primarily on optimizing the DNN components of speech pipeline. We will then show results from a GPU optimized fast lattice decode algorithm to achieve high end to end throughput across the whole ASR pipeline from the acoustic model to the language model.  Back
 
Keywords:
AI Application Deployment and Inference, AI and DL Research, GTC Silicon Valley 2018 - ID S81034
Streaming:
Download:
Share:
Accelerated Analytics
Presentation
Media
Efficient Maximum Flow Algorithm and Applications
Maximizing data flow is one of the most important graph problems and has numerous applications across various computational domains: transportation networks, power routing, image segmentation, social network clustering, and recommendation systems. There are many efficient algorithms that have been developed for this problem, most of them trying to minimize computational complexity. However, not all these algorithms map well to massively parallel architectures like GPUs. We'll present a novel GPU-friendly approach based on the MPM algorithm that achieves from 5 to 20 times speedup over the state-of-the-art multithreaded CPU implementation from Galois library on general graphs with various diameters. We'll also discuss some real-world applications of the maximum flow problem in computer vision for image segmentation and in data analytics to find communities in social networks.
Maximizing data flow is one of the most important graph problems and has numerous applications across various computational domains: transportation networks, power routing, image segmentation, social network clustering, and recommendation systems. There are many efficient algorithms that have been developed for this problem, most of them trying to minimize computational complexity. However, not all these algorithms map well to massively parallel architectures like GPUs. We'll present a novel GPU-friendly approach based on the MPM algorithm that achieves from 5 to 20 times speedup over the state-of-the-art multithreaded CPU implementation from Galois library on general graphs with various diameters. We'll also discuss some real-world applications of the maximum flow problem in computer vision for image segmentation and in data analytics to find communities in social networks.  Back
 
Keywords:
Accelerated Analytics, Algorithms and Numerical Techniques, GTC Silicon Valley 2017 - ID S7370
Download:
Share:
Deep Learning and AI
Presentation
Media
Speech Recognition Using the GPU Accelerated Kaldi Framework
NVIDIA and John Hopkins have partnered up to accelerated speech recognition within the popular Kaldi framework. This framework is the de facto standard when it comes to transcoding recorded audio into the written text. Early results have shown NVIDIA GPUs can provide substantial speedups over pure CPU implementations. This talk will focus on the progress of this effort and the value that GPU acceleration adds to speech recognition.
NVIDIA and John Hopkins have partnered up to accelerated speech recognition within the popular Kaldi framework. This framework is the de facto standard when it comes to transcoding recorded audio into the written text. Early results have shown NVIDIA GPUs can provide substantial speedups over pure CPU implementations. This talk will focus on the progress of this effort and the value that GPU acceleration adds to speech recognition.   Back
 
Keywords:
Deep Learning and AI, Accelerated Data Science, GTC Washington D.C. 2018 - ID DC8189
Streaming:
Share: