@article{Stan2011442,
  author = {Adriana Stan and Junichi Yamagishi and Simon King and
                   Matthew Aylett},
  title = {The {R}omanian speech synthesis ({RSS}) corpus:
                   Building a high quality {HMM}-based speech synthesis
                   system using a high sampling rate},
  journal = {Speech Communication},
  volume = {53},
  number = {3},
  pages = {442--450},
  note = {},
  abstract = {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 96 kHz 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 substantial differences to the quality
                   of the synthetic speech. Contrary to common practice in
                   automatic speech recognition, higher waveform sampling
                   frequencies can offer enhanced feature extraction and
                   improved speaker similarity for HMM-based speech
                   synthesis.},
  doi = {10.1016/j.specom.2010.12.002},
  issn = {0167-6393},
  keywords = {Speech synthesis, HTS, Romanian, HMMs, Sampling
                   frequency, Auditory scale},
  url = {http://www.sciencedirect.com/science/article/pii/S0167639310002074},
  year = 2011
}