Journal
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
Volume -, Issue -, Pages 7874-7878Publisher
IEEE
DOI: 10.1109/icassp40776.2020.9054099
Keywords
Automatic speech recognition; decoder; WFST; parallel computing; edge
Categories
Ask authors/readers for more resources
We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs). The decoder is efficient in memory utilization, input/output (I/O) bandwidth, and uses a novel Viterbi implementation designed to maximize parallelism. The reduced memory footprint allows the decoder to process significantly larger graphs than previously possible, while optimizing I/O increases the number of simultaneous streams supported. GPU preprocessing of lattice segments enables intermediate lattice results to be returned to the requestor during streaming inference. Collectively, the proposed algorithm yields up to a 240x speedup over single core CPU decoding, and up to 40x faster decoding than the current state-of-the-art GPU decoder, while returning equivalent results. This decoder design enables deployment of production-grade ASR models on a large spectrum of systems, ranging from large data center servers to low-power edge devices.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available