Automatic speech recognition performance in different room acoustic environments with and without dereverberation preprocessing.
Alexandros TsilfidisIosif MporasJohn MourjopoulosNikos FakotakisPublished in: Comput. Speech Lang. (2013)
Keyphrases
- automatic speech recognition
- preprocessing
- acoustic features
- speech sounds
- speech recognition
- speech recognizers
- acoustic models
- speech segments
- speech signal
- hidden markov models
- speech retrieval
- word error rate
- conversational speech
- broadcast news
- speaker independent
- recognition errors
- spoken words
- speech recognition systems
- formant frequencies
- real environment
- word recognition
- speech corpus
- noisy environments
- language model
- spontaneous speech
- document retrieval
- multi modal
- feature extraction