{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:21Z","timestamp":1774419681963,"version":"3.50.1"},"reference-count":23,"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\/icassp49660.2025.10887661","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Compact Neural TTS Voices for Accessibility"],"prefix":"10.1109","author":[{"given":"Kunal","family":"Jain","sequence":"first","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eoin","family":"Murphy","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepanshu","family":"Gupta","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Dyke","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saumya","family":"Shah","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasilieios","family":"Tsiaras","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petko","family":"Petkov","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair","family":"Conkie","sequence":"additional","affiliation":[{"name":"Apple Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IGEHT.2017.8094103"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2010.5606343"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/17483107.2019.1629111"},{"issue":"23","key":"ref4","article-title":"Influence of TTS Systems Performance on Reaction Times in People with Aphasia","volume-title":"Applied Sciences","volume":"11","author":"Cistola","year":"2021"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-1192","article-title":"Livespeech: Low-latency zero-shot text-to-speech via autoregressive modeling of audio discrete codes","author":"Dang","year":"2024"},{"key":"ref6","first-page":"1234","article-title":"Speech Synthesis Based on Hidden Markov Models","volume-title":"Proceedings of the IEEE","volume":"101","author":"Tokuda"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/ICASSP.1996.541110","article-title":"Unit selection in a concatenative speech synthesis system using a large speech database","volume-title":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","volume":"1","author":"Hunt"},{"key":"ref8","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref9","first-page":"287","article-title":"Normalization of non-standard words","volume-title":"Comput. Speech Lang.","volume":"15","author":"Sproat","year":"2001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_12"},{"key":"ref12","article-title":"Building voices in the Festival speech synthesis system","author":"Black","year":"2000"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9054560","article-title":"Scalable Multilingual Frontend for TTS","author":"Conkie","year":"2020"},{"key":"ref14","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","author":"Ren","year":"2022"},{"key":"ref15","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"International Conference on Machine Learning","author":"Kalchbrenner"},{"key":"ref16","article-title":"Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation","author":"Kasai","year":"2021"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.sustainlp-1.5","article-title":"Lessons on Parameter Sharing across Layers in Transformers","author":"Takase","year":"2023"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.741","article-title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","author":"Ge","year":"2022"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.acl-short.1","article-title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","author":"Zaken","year":"2022"},{"key":"ref20","article-title":"Linear symmetric quantization of neural networks for low-precision integer hardware","volume-title":"International Conference on Learning Representations","author":"Zhao"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688154"},{"key":"ref22","article-title":"Epitran: Precision G2P for many languages","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","author":"Mortensen"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2019-2441","article-title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","author":"Zen","year":"2019"}],"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\/10887661.pdf?arnumber=10887661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:05Z","timestamp":1774416245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887661","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}