GTC 2020 S21832
Presenters: Hugo Braun,NVIDIA
Abstract
Automatic speech recognition (ASR) algorithms allow us to interact with devices, appliances, and services using spoken language. Used in cloud services like Siri, Google Voice, and Amazon Echo, speech recognition is growing in popularity, which substantially increases the computational demand for ASR inference. We are now bringing low-latency online ASR support to our GPU-accelerated pipeline, bringing order-of-magnitude speedups to your existing Kaldi models. That technology is available both in the data center for a high-throughput ASR cloud service, and at the edge on our low-power embedded devices from the Jetson family.
Watch this session
Join in the conversation below.