Third International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2003)
This paper proposes and evaluates a new direct speech transform method with waveforms from laryngectomee speech to normal speech. Most conventional speech recognition systems and speech processing systems are not able to treat laryngectomee speech with satisfactory results. One of the major causes is difficulty preparing corpora. It is very hard to record a large amount of clear and intelligible utterance data because the acoustical quality depends strongly on the individual status of such people. Our proposed method focuses on the acoustic characteristics of speech waveform of laryngectomee people and transforms such characteristics directly into normal speech. The proposed method is able to deal with esophageal and alaryngeal speech in the same algorithm. The method is realized by learning transform rules that have acoustic correspondences between laryngectomee and normal speech. Results of several fundamental experiments indicate a promising performance for real transform.
Index Terms. Esophageal speech, Alaryngeal speech, Speech transform, Transform rule, Acoustic characteristics of speech
Full Paper (reprinted with permission from Firenze University Press)
Bibliographic reference. Murakami, Koji / Araki, Kenji / Hiroshige, Makoto / Tochinai, Koji (2003): "A study of a direct speech transform method on laryngectomee speech", In MAVEBA-2003, 23-26.