Pronunciation Variant Selection for Spontaneous Speech Synthesis-Listening Effort As a Quality Parameter.
Steffen WernerMatthias WolffRüdiger HoffmannPublished in: ICASSP (1) (2006)
Keyphrases
- speech synthesis
- speech recognition
- input parameters
- text to speech
- higher quality
- automatic speech recognition
- language model
- hidden markov models
- effort needed
- high quality
- data quality
- parameter values
- machine learning
- quality measures
- noisy environments
- conversational speech
- prosodic features
- selection algorithm
- speech signal
- low quality
- parameter settings
- machine translation
- image coding
- pattern recognition
- case study
- feature selection