Direct Acoustics-to-Word Models for English Conversational Speech Recognition.
Kartik AudhkhasiBhuvana RamabhadranGeorge SaonMichael PichenyDavid NahamooPublished in: INTERSPEECH (2017)
Keyphrases
- speech recognition
- speech recognizer
- speech recognition systems
- speech recognition technology
- hidden markov models
- acoustic models
- automatic speech recognition
- spoken language
- speech retrieval
- keyword spotting
- language model
- word error rate
- speech synthesis
- wall street journal corpus
- speech signal
- handwriting recognition
- conversational speech
- isolated word
- pattern recognition
- speech recognizers
- english language
- speech processing
- natural language
- broadcast news
- translation model
- word recognition
- noisy environments
- wordnet
- probabilistic model