{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:39:21Z","timestamp":1776886761503,"version":"3.51.2"},"reference-count":31,"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\/iscslp63861.2024.10800477","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"646-650","source":"Crossref","is-referenced-by-count":2,"title":["Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Yang","sequence":"first","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Peng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xionghu","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","volume":"1","author":"Mann","year":"2020","journal-title":"arXiv preprint"},{"issue":"240","key":"ref2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","volume-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Le Scao","year":"2023"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models (2023)","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"28492","article-title":"Robust speech recognition via large-scale weak su-pervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/421"},{"key":"ref13","article-title":"Multi-resolution hubert: Multi-resolution speech self-supervised learning with masked unit prediction","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref15","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref20","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref24","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref26","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref29","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"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\/10800477.pdf?arnumber=10800477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:31Z","timestamp":1735021591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800477","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}