Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin.
Dario AmodeiSundaram AnanthanarayananRishita AnubhaiJingliang BaiEric BattenbergCarl CaseJared CasperBryan CatanzaroJingdong ChenMike ChrzanowskiAdam CoatesGreg DiamosErich ElsenJesse H. EngelLinxi FanChristopher FougnerAwni Y. HannunBilly JunTony HanPatrick LeGresleyXiangang LiLibby LinSharan NarangAndrew Y. NgSherjil OzairRyan PrengerSheng QianJonathan RaimanSanjeev SatheeshDavid SeetapunShubho SenguptaChong WangYi WangZhiqian WangBo XiaoYan XieDani YogatamaJun ZhanZhenyao ZhuPublished in: ICML (2016)
Keyphrases
- speech recognition
- end to end
- speech recognition technology
- automatic speech recognition
- speaker independent
- broadcast news
- speech signal
- hidden markov models
- speech synthesis
- isolated word
- speech processing
- speech recognizer
- pattern recognition
- speech recognition systems
- speaker identification
- natural language
- language model
- machine translation
- noisy environments
- speaker dependent
- language identification
- english text
- noisy speech
- speech retrieval
- word error rate
- neural network
- text to speech
- vocal tract
- speaker adaptation
- cross language
- spoken document retrieval
- speech recognition errors
- cross lingual
- spoken language