Streaming Sequence Transduction through Dynamic Compression

Benjamin Van Durme; Guanghui Qin; Haoran Xu; Heidi C. Zhang; Philipp Koehn; Tongfei Chen; Weiting Tan; Yunmo Chen

Streaming Sequence Transduction through Dynamic Compression

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 2402.01172 v3 pith:ZDCTKAJT submitted 2024-02-02 cs.CL cs.SDeess.AS

Weiting Tan , Yunmo Chen , Tongfei Chen , Guanghui Qin , Haoran Xu , Heidi C. Zhang , Benjamin Van Durme , Philipp Koehn This is my paper · ORCID

classification cs.CLcs.SDeess.AS

keywords startransductionanchorcompressionrepresentationsstreamsachievingautomatic

verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments

read the original abstract

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor representations, achieving nearly lossless compression (12x) in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous speech-to-text tasks, optimizing latency, memory footprint, and quality.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
cs.CL 2024-12 conditional novelty 6.0 of 10

A survey of 110 SimulST papers shows most systems rely on unrealistic human pre-segmented audio and inconsistent terminology, and it offers a taxonomy and recommendations to fix both.

Pith tools