{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:38Z","timestamp":1776888398421,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888963","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Lightweight neural front-ends for low-resource on-device Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Giulia","family":"Comini","sequence":"first","affiliation":[{"name":"Amazon AGI,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heereen","family":"Shim","sequence":"additional","affiliation":[{"name":"Amazon AGI,Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel Sam","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Amazon AGI,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.1998-39"},{"key":"ref2","article-title":"Issues in building general letter to sound rules","volume-title":"The third ESCA\/COCOSDA workshop (ETRW) on speech synthesis","author":"Black"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0169"},{"key":"ref4","article-title":"A Multi-lingual TN\/ITN Framework for Speech Technology","volume":"10","author":"Cho","year":"2000","journal-title":"Language"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324914000175"},{"key":"ref6","first-page":"4857","article-title":"NeMo (Inverse) Text Normalization: From Development to Production","volume-title":"Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021","author":"Zhang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5403"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1954"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"key":"ref10","article-title":"Multilingual context-based pronunciation learning for Text-to-Speech","volume-title":"CoRR","volume":"abs\/2307.16709","author":"Comini","year":"2023"},{"key":"ref11","article-title":"RNN approaches to text normalization: A challenge","author":"Sproat","year":"2016"},{"key":"ref12","article-title":"Deepnorm-a deep learning approach to text normalization","author":"Zare","year":"2017"},{"key":"ref13","article-title":"A unified transformer-based framework for duplex text normalization","author":"Lai","year":"2021"},{"issue":"140","key":"ref14","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume-title":"Journal of Machine Learning Research","volume":"21","author":"Raffel","year":"2020"},{"key":"ref15","article-title":"Bidirectional Language Models Are Also Few-shot Learners","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Patel"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-industry.10"},{"key":"ref18","article-title":"Better speech synthesis through scaling","volume-title":"CoRR","volume":"abs\/2305.07243","author":"Betker","year":"2023"},{"key":"ref19","article-title":"BASE TTS: lessons from building a billion-parameter text-to-speech model on 100k hours of data","volume-title":"CoRR","volume":"abs\/2402.08093","author":"L","year":"2024"},{"key":"ref20","article-title":"A Chat About Boring Problems: Studying GPTbased text normalization","volume-title":"CoRR","volume":"abs\/2309.13426","author":"Zhang","year":"2023"},{"key":"ref21","article-title":"GPT-4 technical report","volume-title":"CoRR","volume":"abs\/2303.08774","year":"2023"},{"key":"ref22","article-title":"Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts","volume-title":"CoRR","volume":"abs\/2306.11372","author":"Nguyen","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/info14120638"},{"key":"ref24","article-title":"LLM Augmented LLMs: Expanding Capabilities through Composition","volume-title":"CoRR","volume":"abs\/2401.02412","author":"Bansal","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414403"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2867"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-188"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-35"},{"key":"ref30","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","author":"Bahdanau"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sigmorphon-1.2"},{"key":"ref32","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke"},{"key":"ref33","first-page":"103","article-title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","volume-title":"Proceedings of SSST@EMNLP 2014, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, 25 October 2014","author":"Cho"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref35","article-title":"Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings","volume-title":"CoRR","volume":"abs\/2307.16643","author":"Ribeiro","year":"2023"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888963.pdf?arnumber=10888963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:49Z","timestamp":1774416229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888963","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}