Pith. sign in

REVIEW 2 cited by

Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.05807 v3 pith:6TCFIKD7 submitted 2022-06-12 cs.CL

Sara Papi , Marco Gaido , Matteo Negri , Marco Turchi This is my paper · ORCID
classification cs.CL
keywords systemsaveragelagginglength-adaptiveover-generationsimulstsimultaneousspeech
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Simultaneous speech translation (SimulST) systems aim at generating their output with the lowest possible latency, which is normally computed in terms of Average Lagging (AL). In this paper we highlight that, despite its widespread adoption, AL provides underestimated scores for systems that generate longer predictions compared to the corresponding references. We also show that this problem has practical relevance, as recent SimulST systems have indeed a tendency to over-generate. As a solution, we propose LAAL (Length-Adaptive Average Lagging), a modified version of the metric that takes into account the over-generation phenomenon and allows for unbiased evaluation of both under-/over-generating systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice

    cs.CL 2025-07 conditional novelty 6.0 of 10

    An end-to-end simultaneous speech-to-speech translation model with voice cloning, trained with a two-stage reinforcement learning reward scheme, reports high accuracy and low latency on the authors' RealSI benchmark.

  2. High-Fidelity Simultaneous Speech-To-Speech Translation

    cs.CL 2025-02 conditional novelty 6.0 of 10

    A decoder-only multistream model with perplexity-based alignment achieves state-of-the-art French-English simultaneous speech-to-speech translation with close-to-human naturalness and voice fidelity.

Pith tools