作者位次 #2/6ACL 2026Poster· Natural Language Processing
LLM - F orced A ligner: A Non-Autoregressive and Accurate LLM -Based Forced Aligner for Multilingual and Long-Form Speech
Bingshen Mu · Xian Shi · Xiong Wang · Hexin Liu · Jin Xu · Lei Xie
摘要
Forced alignment (FA) predicts start and end timestamps for words or characters in speech, but existing methods are language-specific and prone to cumulative temporal shifts. The multilingual speech understanding and long-sequence processing abilities of speech large language models (SLLMs) make...