Saved in:
Bibliographic Details
Main Authors: Wilmet, Vincent, Du, Johnson
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.00965
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917775471017984
author Wilmet, Vincent
Du, Johnson
author_facet Wilmet, Vincent
Du, Johnson
contents This paper presents an in-depth analysis of the latency characteristics observed in simultaneous speech-to-speech model's performance, particularly focusing on hallucination-induced latency spikes. By systematically experimenting with various input parameters and conditions, we propose methods to minimize latency spikes and improve overall performance. The findings suggest that a combination of careful input management and strategic parameter adjustments can significantly enhance speech-to-speech model's latency behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00965
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What does it take to get state of the art in simultaneous speech-to-speech translation?
Wilmet, Vincent
Du, Johnson
Computation and Language
This paper presents an in-depth analysis of the latency characteristics observed in simultaneous speech-to-speech model's performance, particularly focusing on hallucination-induced latency spikes. By systematically experimenting with various input parameters and conditions, we propose methods to minimize latency spikes and improve overall performance. The findings suggest that a combination of careful input management and strategic parameter adjustments can significantly enhance speech-to-speech model's latency behavior.
title What does it take to get state of the art in simultaneous speech-to-speech translation?
topic Computation and Language
url https://arxiv.org/abs/2409.00965