Turbocharge Speech Understanding with Pilot Inference
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.
Authors
- Rongxiang Wang (ORCID: https://orcid.org/0009-0002-6029-5317)
- Felix Xiaozhu Lin (ORCID: https://orcid.org/0009-0000-0081-6411)
Institutions
- University of Virginia (US)
Publication Details
- Published
- 2024-12-04
- DOI
- https://doi.org/10.1145/3636534.3690694
- Citations
- 3
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 1.04
Funders
- National Science Foundation