Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction
基于常见词提示和偏置词位置预测的语音LLM上下文偏置
专题命中 预训练与数据 :LLM(title,title_cn)
AI总结 本文提出基于声音线索的上下文偏置方法,利用常见词发音相似性提升稀有词识别,通过多输出学习增强鲁棒性,实验显示在基准系统基础上错误率降低16.3%。
Comments Copyright 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works