DNN-based performance measures for predicting error rates in automatic speech recognition and optimizing hearing aid parameters.
Angel Mario Castro MartinezLukas GerlachGuillermo Payá VayáHynek HermanskyJasper OosterBernd T. MeyerPublished in: Speech Commun. (2019)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- broadcast news
- speech retrieval
- conversational speech
- noisy environments
- recognition errors
- maximum likelihood
- hidden markov models
- bayesian networks
- word error rate
- spontaneous speech
- word recognition
- multi modal
- error rate
- natural language
- pattern recognition
- speech corpus
- computer vision
- spoken words