Attention or convolution: Transformer encoders in audio language models for inference efficiency

Abstract:
No abstract specified

SEEK ID: https://publications.h-its.org/publications/1789

Research Groups: Natural Language Processing

Publication type: InProceedings

Citation: Proceedings of the Workshop on Self-supervision in Audio, Speech and Beyond at IEEE ICASSP, Seoul, South Korea, 14 April 2024.

Date Published: 14th Apr 2024

URL: https://arxiv.org/pdf/2311.02772.pdf

Registered Mode: manually

Authors: Sungho Jeon, Ching-Feng Yeh, Hakan Inan, Wei-Ning Hsu, Rashi Rungta, Yashar Mehdad, Daniel Bikel

help Submitter
Activity

Views: 532

Created: 14th Feb 2024 at 09:43

Last updated: 29th May 2024 at 13:43

help Tags

This item has not yet been tagged.

help Attributions

None

Powered by
(v.1.14.2)
Copyright © 2008 - 2023 The University of Manchester and HITS gGmbH