On-line experimental methods to evaluate text-to-speech (TTS) synthesis: effects of voice gender and signal quality on intelligibility, naturalness and preference.
Catherine J. StevensNicole LeesJulie VonwillerDenis BurnhamPublished in: Comput. Speech Lang. (2005)
Keyphrases
- text to speech
- speech synthesis
- benchmark datasets
- high quality
- real world
- computational cost
- word processing
- quality measures
- text to speech synthesis
- machine learning methods
- qualitative and quantitative
- high frequency
- individual differences
- frequency domain
- empirical studies
- signal processing
- significant improvement