Improving Acoustic Models for Russian Spontaneous Speech Recognition.
Alexey PrudnikovIvan MedennikovValentin MendelevMaxim KorenevskyYuri Y. KhokhlovPublished in: SPECOM (2015)
Keyphrases
- speech recognition
- acoustic models
- speech recognizer
- speaker independent
- automatic speech recognition
- hidden markov models
- speech signal
- language model
- conversational speech
- pattern recognition
- speaker identification
- noisy environments
- speech recognition systems
- multi modal
- neural network
- training data
- image processing
- machine learning