Allophones in automatic whispery speech recognition
- 26 September 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 811-815
Abstract
The article presents studies on the automatic whispery speech recognition. In the performed research a new corpus with whispery speech has been used. It has been checked whether the extended set of articulatory units (allophones have been used instead of phonemes) improves quality of whispery speech recognition. Experimental results show that the small changes in the allophone set may provide better speech recognition quality than using phonemes approach. The authors also made available the trained g2p (grapheme-to-phoneme) model of Polish language for the Sequitur toolkit.Keywords
This publication has 7 references indexed in Scilit:
- Impact of vocal effort variability on automatic speech recognitionSpeech Communication, 2012
- Reconstruction of Normal Sounding Speech for Laryngectomy Patients Through a Modified CELP CodecIEEE Transactions on Biomedical Engineering, 2010
- Joint-sequence models for grapheme-to-phoneme conversionSpeech Communication, 2008
- OpenFst: A General and Efficient Weighted Finite-State Transducer Library2007
- Analysis and recognition of whispered speechSpeech Communication, 2005
- Allophone clustering for continuous speech recognition2002
- A new prosthesis for voice rehabilitation after laryngectomyEuropean Archives of Oto-Rhino-Laryngology, 1982