Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition.
Kartik AudhkhasiBrian KingsburyBhuvana RamabhadranGeorge SaonMichael PichenyPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- speech recognizer
- speech recognition systems
- spoken language
- speech recognition technology
- wall street journal corpus
- speech recognizers
- acoustic models
- pattern recognition
- keyword spotting
- speech signal
- automatic speech recognition
- noisy environments
- speech processing
- hidden markov models
- word error rate
- english language
- language learning
- language model
- probabilistic model
- feature extraction
- speaker identification
- broadcast news
- machine learning
- handwriting recognition
- multi modal
- isolated word
- information retrieval