{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:21:22Z","timestamp":1776889282278,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434682","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation"],"prefix":"10.1109","author":[{"given":"Tianlun","family":"Zuo","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Jingbin","family":"Hu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Yuke","family":"Li","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Xinfa","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"iQIYI, Inc,Chengdu,China"}]},{"given":"Ying","family":"Yan","sequence":"additional","affiliation":[{"name":"iQIYI, Inc,Chengdu,China"}]},{"given":"Junhui","family":"Liu","sequence":"additional","affiliation":[{"name":"iQIYI, Inc,Chengdu,China"}]},{"given":"Danming","family":"Xie","sequence":"additional","affiliation":[{"name":"iQIYI, Inc,Chengdu,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref2","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2103.00993"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2021-14"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning.","author":"Kim"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0797"},{"key":"ref6","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.03926"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref8","article-title":"Zero-shot crosslingual voice transfer for tts","author":"Biadsy","year":"2024","journal-title":"arXiv preprint arXiv:2409.13910"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2023.1230755"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-363"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313413"},{"key":"ref12","article-title":"Llasa: Scaling traintime and inference-time compute for llama-based speech synthesis","volume-title":"arXiv preprint arXiv:2502.04128","author":"Ye","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2021-14"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-754"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref18","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3363444"},{"key":"ref20","article-title":"Cosyvoice 3: Towards in-the-wild speech generation via scaling-up and post-training","author":"Du","year":"2025"},{"key":"ref21","article-title":"Maskgct: Zero-shot text-to-speech with masked generative codec transformer","author":"Wang","year":"2024"},{"key":"ref22","article-title":"Glm-4-voice: Towards intelligent and human-like end-to-end spoken chatbot","author":"Zeng","year":"2024"},{"key":"ref23","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref24","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11208937"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.613"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34761"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3372152"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095105"},{"key":"ref30","article-title":"Typhoon 2: A family of open text and multimodal thai large language models","author":"Pipatanakul","year":"2024","journal-title":"arXiv preprint arXiv:2412.13702"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref32","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023","journal-title":"arXiv preprint arXiv:2310.11230"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434682.pdf?arnumber=11434682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:07Z","timestamp":1775192287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434682","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}