Work

Turbocharge Speech Understanding with Pilot Inference

Year: 2024

Type: conference-paper

Abstract: Modern speech understanding (SU) runs a sophisticated pipeline: ingesting streaming voice input, the pipeline executes encoder-decoder based deep neural networks repeatedly; by doing so, the pipeline generates tentative outputs (called hypotheses), and periodically scores the hypotheses.

Source: Proceedings of the 28th Annual International Conference on Mobile Computing And Networking

DOI: 10.1145/3636534.3690694

Authors: Rongxiang Wang, Felix Xiaozhu Lin

Institution: University of Virginia

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: Collaborative Research: CNS Core: Medium: Understanding and Strengthening Memory Security for Non-Volatile Memory, CAREER: A Trustworthy and Verifiable Software Backplane for the Cloud Edge, SPX: Write Once, Run on Anything: Verified, Tuned Accelerator Kernels from High Level Specifications