{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:13:47Z","timestamp":1735103627935,"version":"3.32.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800167","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"441-445","source":"Crossref","is-referenced-by-count":0,"title":["NLPP: A Natural Language Prosodic Prominence Dataset Assisted by ChatGPT"],"prefix":"10.1109","author":[{"given":"Rui","family":"Niu","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhe","family":"Song","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref2","article-title":"Speech synthesis with mixed emotions","volume-title":"IEEE Transactions on Affective Computing","author":"Zhou","year":"2022"},{"key":"ref3","first-page":"10970","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Mega-tts 2: Zero-shot text-to-speech with arbitrary length speech prompts","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3402088"},{"key":"ref8","article-title":"Prompttts 2: De-scribing and generating voices with text prompt","author":"Leng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"5180","article-title":"Style tokens: Un-supervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang","year":"2018"},{"key":"ref10","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-465"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/01690961003589492"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/978-94-015-9413-4_5","article-title":"The perception of prosodic promi-nence","volume-title":"Prosody: Theory and experiment: Studies presented to G\u00f6sta Bruce","author":"Terken","year":"2000"},{"key":"ref14","first-page":"681","article-title":"GPT-3: Its nature, scope, limits, and consequences","volume-title":"Minds and Machines","volume":"30","author":"Floridi","year":"2020"},{"key":"ref15","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Gpt-ner: Named entity recognition via large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Wavcaps: A chatgpt-assisted weakly-labelled audio captioning dataset for audio-language multimodal research","volume-title":"arXiv preprint","author":"Mei","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.001"},{"key":"ref22","first-page":"281","article-title":"Predicting Prosodic Prominence from Text with Pretrained Contextualized Word Representations","volume-title":"Proceedings of the 22nd Nordic Conference on Computational Linguistics","author":"Talman","year":"2019"},{"key":"ref23","first-page":"4171","article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton","year":"2019"},{"key":"ref24","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong","year":"2020"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800167.pdf?arnumber=10800167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:14Z","timestamp":1735021574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800167","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}