Comparing Front-End Enhancement Techniques and Multiconditioned Training for Robust Automatic Speech Recognition.
Meet H. SoniSonal JoshiAshish PandaPublished in: TSD (2019)
Keyphrases
- automatic speech recognition
- speech recognition
- noisy environments
- discriminative training
- speech signal
- conversational speech
- word error rate
- image processing
- speech retrieval
- recognition errors
- word recognition
- hidden markov models
- machine learning
- spoken words
- broadcast news
- training process
- maximum likelihood
- multiresolution