Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition.
Ye BaiJingping ChenJitong ChenWei ChenZhuo ChenChuang DingLinhao DongQianqian DongYujiao DuKepan GaoLu GaoYi GuoMinglun HanTing HanWenchao HuXinying HuYuxiang HuDeyu HuaLu HuangMingkun HuangYoujia HuangJishuo JinFanliu KongZongwei LanTianyu LiXiaoyang LiZeyang LiZehua LinRui LiuShouda LiuLu LuYizhou LuJingting MaShengtao MaYulin PeiChen ShenTian TanXiaogang TianMing TuBo WangHao WangYuping WangYuxuan WangHanzhang XiaRui XiaShuangyi XieHongmin XuMeng YangBihong ZhangJun ZhangWanyi ZhangYang ZhangYawei ZhangYijie ZhengMing ZouPublished in: CoRR (2024)
Keyphrases
- speech recognition
- automatic speech recognition
- speech signal
- speech synthesis
- hidden markov models
- speech processing
- pattern recognition
- word error rate
- speech recognizer
- language model
- speech recognition technology
- speech recognition systems
- recognition engine
- speech recognizers
- noisy environments
- speaker identification
- speech retrieval
- handwriting recognition
- noisy speech
- neural network
- isolated word
- speaker independent
- machine learning
- speech recognition errors
- speaker adaptation
- broadcast news
- signal processing