{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:15:56Z","timestamp":1774419356173,"version":"3.50.1"},"reference-count":20,"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\/icassp49660.2025.10888140","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Whisper in Medusa\u2019s Ear: Multi-head Efficient Decoding for Transformer-based ASR"],"prefix":"10.1109","author":[{"given":"Yael","family":"Segal-Feldman","sequence":"first","affiliation":[{"name":"aiOla Research,Israel"}]},{"given":"Aviv","family":"Shamsian","sequence":"additional","affiliation":[{"name":"aiOla Research,Israel"}]},{"given":"Aviv","family":"Navon","sequence":"additional","affiliation":[{"name":"aiOla Research,Israel"}]},{"given":"Gill","family":"Hetz","sequence":"additional","affiliation":[{"name":"aiOla Research,Israel"}]},{"given":"Joseph","family":"Keshet","sequence":"additional","affiliation":[{"name":"aiOla Research,Israel"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","article-title":"Faster whisper: High-performance whisper inference","year":"2023"},{"key":"ref3","article-title":"Ctranslate2","year":"2019"},{"key":"ref4","article-title":"Whisper-kdq: A lightweight whisper via guided knowledge distillation and quantization for efficient asr","author":"Shao","year":"2023"},{"key":"ref5","article-title":"Distil-whisper: Robust knowledge distillation via large-scale pseudo labelling","author":"Gandhi","year":"2023"},{"key":"ref6","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning","author":"Leviathan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.456"},{"key":"ref8","article-title":"Accelerating large language model decoding with speculative sampling","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"ref10","article-title":"Accelerating llm inference with staged speculative decoding","volume-title":"Workshop on Efficient Systems for Foundation Models@ ICML2023","author":"Spector"},{"key":"ref11","article-title":"Blockwise parallel decoding for deep autoregressive models","volume":"31","author":"Stern","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Better & faster large language models via multi-token prediction","volume-title":"Forty-first International Conference on Machine Learning","author":"Gloeckle"},{"key":"ref13","article-title":"Medusa: Simple llm inference acceleration framework with multiple decoding heads","author":"Cai","year":"2024"},{"key":"ref14","article-title":"Kangaroo: Lossless self-speculative decoding via double early exiting","author":"Liu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/9781108963558"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389666"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref20","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"International Conference on Machine Learning","author":"Shazeer"}],"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\/10888140.pdf?arnumber=10888140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:28Z","timestamp":1774416148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888140","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}