Deep Speech 2: End-to-End Speech Recognition in English and Mandarin.
Dario AmodeiRishita AnubhaiEric BattenbergCarl CaseJared CasperBryan CatanzaroJingdong ChenMike ChrzanowskiAdam CoatesGreg DiamosErich ElsenJesse H. EngelLinxi FanChristopher FougnerTony HanAwni Y. HannunBilly JunPatrick LeGresleyLibby LinSharan NarangAndrew Y. NgSherjil OzairRyan PrengerJonathan RaimanSanjeev SatheeshDavid SeetapunShubho SenguptaYi WangZhiqian WangChong WangBo XiaoDani YogatamaJun ZhanZhenyao ZhuPublished in: CoRR (2015)
Keyphrases
- end to end
- speech recognition
- speech recognition technology
- automatic speech recognition
- broadcast news
- speech signal
- speaker independent
- speech synthesis
- speech recognizer
- speech processing
- hidden markov models
- speech recognition systems
- isolated word
- speaker identification
- language model
- word error rate
- pattern recognition
- speech retrieval
- noisy environments
- machine translation
- speech recognizers
- language identification
- natural language
- speaker dependent
- cross lingual
- english text
- spoken language
- keyword spotting
- conversational speech
- speaker adaptation
- speech recognition errors
- speaker diarization
- neural network
- cross language
- acoustic models
- n gram
- information retrieval