@inproceedings{he-etal-2026-hw,
title = "{HW}-{TSC}{'}s Submission to the {IWSLT} 2026 Cross-Lingual Voice Cloning Track",
author = "He, Yu and
Wei, Daimeng and
GUO, Jiaxin and
Luo, Yuanchang and
Shang, Hengchao and
Li, Zongyao and
Rao, Zhiqiang and
Yang, Jinlong and
Wu, Zhanglin and
Huang, Boqi and
Lan, Xiaoqing",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.11/",
pages = "97--102",
ISBN = "979-8-89176-411-8",
abstract = "This paper presents HW-TSC{'}s submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track. The Cross-Lingual Voice Cloning Track includes three target languages: Arabic, Chinese, and French. We take part in two language tasks of this track, namely Chinese and French. We employ the Qwen3-TTS-12Hz-1.7B-Base multilingual model as the core voice cloning model. To tackle problems such as excessively long duration of the original reference audio and scattered features, we design a sliding-window audio segmentation preprocessing method, which continuously splits long audio into standardized short segments with overlapping redundancy. This method avoids feature attenuation caused by overly long audio and maximizes the preservation of complete timbre information through step overlap. To select the outputs with the highest timbre similarity from numerous synthetic results, this study conducts voiceprint recognition based on the Enhanced Context-Dependent Adversarial Time Delay Neural Network (ECAPA-TDNN), with cosine similarity as the core quantitative evaluation metric, and selects the result with the highest similarity as the optimal output."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2026-hw">
<titleInfo>
<title>HW-TSC’s Submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">GUO</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanchang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinlong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)</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">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<abstract>This paper presents HW-TSC’s submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track. The Cross-Lingual Voice Cloning Track includes three target languages: Arabic, Chinese, and French. We take part in two language tasks of this track, namely Chinese and French. We employ the Qwen3-TTS-12Hz-1.7B-Base multilingual model as the core voice cloning model. To tackle problems such as excessively long duration of the original reference audio and scattered features, we design a sliding-window audio segmentation preprocessing method, which continuously splits long audio into standardized short segments with overlapping redundancy. This method avoids feature attenuation caused by overly long audio and maximizes the preservation of complete timbre information through step overlap. To select the outputs with the highest timbre similarity from numerous synthetic results, this study conducts voiceprint recognition based on the Enhanced Context-Dependent Adversarial Time Delay Neural Network (ECAPA-TDNN), with cosine similarity as the core quantitative evaluation metric, and selects the result with the highest similarity as the optimal output.</abstract>
<identifier type="citekey">he-etal-2026-hw</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.11/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>97</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track
%A He, Yu
%A Wei, Daimeng
%A GUO, Jiaxin
%A Luo, Yuanchang
%A Shang, Hengchao
%A Li, Zongyao
%A Rao, Zhiqiang
%A Yang, Jinlong
%A Wu, Zhanglin
%A Huang, Boqi
%A Lan, Xiaoqing
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F he-etal-2026-hw
%X This paper presents HW-TSC’s submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track. The Cross-Lingual Voice Cloning Track includes three target languages: Arabic, Chinese, and French. We take part in two language tasks of this track, namely Chinese and French. We employ the Qwen3-TTS-12Hz-1.7B-Base multilingual model as the core voice cloning model. To tackle problems such as excessively long duration of the original reference audio and scattered features, we design a sliding-window audio segmentation preprocessing method, which continuously splits long audio into standardized short segments with overlapping redundancy. This method avoids feature attenuation caused by overly long audio and maximizes the preservation of complete timbre information through step overlap. To select the outputs with the highest timbre similarity from numerous synthetic results, this study conducts voiceprint recognition based on the Enhanced Context-Dependent Adversarial Time Delay Neural Network (ECAPA-TDNN), with cosine similarity as the core quantitative evaluation metric, and selects the result with the highest similarity as the optimal output.
%U https://aclanthology.org/2026.iwslt-1.11/
%P 97-102
Markdown (Informal)
[HW-TSC’s Submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track](https://aclanthology.org/2026.iwslt-1.11/) (He et al., IWSLT 2026)
ACL
- Yu He, Daimeng Wei, Jiaxin GUO, Yuanchang Luo, Hengchao Shang, Zongyao Li, Zhiqiang Rao, Jinlong Yang, Zhanglin Wu, Boqi Huang, and Xiaoqing Lan. 2026. HW-TSC’s Submission to the IWSLT 2026 Cross-Lingual Voice Cloning Track. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 97–102, San Diego, USA (in-person and online). Association for Computational Linguistics.