Streaming Sequence Transduction through Dynamic Compression

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

doi:10.18653/v1/2025.iwslt-1.1

Streaming Sequence Transduction through Dynamic Compression

Weiting Tan, Yunmo Chen, Tongfei Chen, Guanghui Qin, Haoran Xu, Chenyu Zhang, Benjamin Van Durme, Philipp Koehn

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

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 (12x) compression in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous Speech Translation, optimizing latency, memory footprint, and quality.

Anthology ID:: 2025.iwslt-1.1
Volume:: Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
Month:: July
Year:: 2025
Address:: Vienna, Austria (in-person and online)
Editors:: Elizabeth Salesky, Marcello Federico, Antonis Anastasopoulos
Venues:: IWSLT | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1–18
Language:
URL:: https://aclanthology.org/2025.iwslt-1.1/
DOI:: 10.18653/v1/2025.iwslt-1.1
Bibkey:
Cite (ACL):: Weiting Tan, Yunmo Chen, Tongfei Chen, Guanghui Qin, Haoran Xu, Chenyu Zhang, Benjamin Van Durme, and Philipp Koehn. 2025. Streaming Sequence Transduction through Dynamic Compression. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 1–18, Vienna, Austria (in-person and online). Association for Computational Linguistics.
Cite (Informal):: Streaming Sequence Transduction through Dynamic Compression (Tan et al., IWSLT 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.iwslt-1.1.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{tan-etal-2025-streaming,
    title = "Streaming Sequence Transduction through Dynamic Compression",
    author = "Tan, Weiting  and
      Chen, Yunmo  and
      Chen, Tongfei  and
      Qin, Guanghui  and
      Xu, Haoran  and
      Zhang, Chenyu  and
      Van Durme, Benjamin  and
      Koehn, Philipp",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Anastasopoulos, Antonis",
    booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.iwslt-1.1/",
    doi = "10.18653/v1/2025.iwslt-1.1",
    pages = "1--18",
    ISBN = "979-8-89176-272-5",
    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 (12x) compression in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous Speech Translation, optimizing latency, memory footprint, and quality."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2025-streaming">
    <titleInfo>
        <title>Streaming Sequence Transduction through Dynamic Compression</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weiting</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunmo</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tongfei</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guanghui</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haoran</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenyu</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Benjamin</namePart>
        <namePart type="family">Van Durme</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-272-5</identifier>
    </relatedItem>
    <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 (12x) compression in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous Speech Translation, optimizing latency, memory footprint, and quality.</abstract>
    <identifier type="citekey">tan-etal-2025-streaming</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.1</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.1/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1</start>
            <end>18</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Streaming Sequence Transduction through Dynamic Compression
%A Tan, Weiting
%A Chen, Yunmo
%A Chen, Tongfei
%A Qin, Guanghui
%A Xu, Haoran
%A Zhang, Chenyu
%A Van Durme, Benjamin
%A Koehn, Philipp
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F tan-etal-2025-streaming
%X 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 (12x) compression in Automatic Speech Recognition (ASR) and outperforming existing methods. Moreover, STAR demonstrates superior segmentation and latency-quality trade-offs in simultaneous Speech Translation, optimizing latency, memory footprint, and quality.
%R 10.18653/v1/2025.iwslt-1.1
%U https://aclanthology.org/2025.iwslt-1.1/
%U https://doi.org/10.18653/v1/2025.iwslt-1.1
%P 1-18

Download as File

Markdown (Informal)

[Streaming Sequence Transduction through Dynamic Compression](https://aclanthology.org/2025.iwslt-1.1/) (Tan et al., IWSLT 2025)

Streaming Sequence Transduction through Dynamic Compression (Tan et al., IWSLT 2025)

ACL

Weiting Tan, Yunmo Chen, Tongfei Chen, Guanghui Qin, Haoran Xu, Chenyu Zhang, Benjamin Van Durme, and Philipp Koehn. 2025. Streaming Sequence Transduction through Dynamic Compression. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 1–18, Vienna, Austria (in-person and online). Association for Computational Linguistics.