The Romanian speech synthesis (RSS) corpus: Building a high quality HMM-based speech synthesis system using a high sampling rate

This paper first introduces a newly-recorded high quality Romanian speech corpus designed for speech synthesis, called “RSS”, along with Romanian front-end text processing modules and HMM-based synthetic voices built from the corpus. All of these are now freely available for academic use in order to promote Romanian speech technology research. The RSS corpus comprises 3500 training sentences and 500 test sentences uttered by a female speaker and was recorded using multiple microphones at 96kHz sampling frequency in a hemianechoic chamber. The details of the new Romanian text processor we have developed are also given. Using the database, we then revisit some basic configuration choices of speech synthesis, such as waveform sampling frequency and auditory frequency warping scale, with the aim of improving speaker similarity, which is an acknowledged weakness of current HMM-based speech synthesisers. As we demonstrate using perceptual tests, these configuration choices can make s...

• Type: Journal
• Year: 2011
• Where: SPEECH
• Authors: Adriana Stan, Junichi Yamagishi, Simon King, Matthew P. Aylett
• Keywords: HMM-based Speech, Romanian Speech, Security Privacy, SPEECH 2011, Speech Synthesis