Study of Sound Clarity Method for Body Conducted Speech using Linear Predictive in Sub-word, and Sound Quality Evaluation by means of Articulatory Feature Analysis
-
- FUKUI Kazutoshi
- Graduate School of Information Sciences, Hiroshima City University
-
- ISHIMITSU Shunsuke
- Graduate School of Information Sciences, Hiroshima City University
-
- NAGOSHI Hayato
- Graduate School of Information Sciences, Hiroshima City University
-
- YAMANAKA Takahiro
- Graduate School of Information Sciences, Hiroshima City University
Bibliographic Information
- Other Title
-
- 体内伝導音のサブワード単位線形予測による音質明瞭化と調音素性分析を用いた評価
Abstract
Japan is presently aging more rapidly than anywhere else in the world. Concurrently, the number of patients suffering speech disorders is increasing every year, and the incidence is higher as age increases. Those suffering from speech disordered face problems with communicating in daily conversation. They are often able to communicate with speech substitutes, but these typically do not provide a sufficient sound frequency range to be understood in conversation. Therefore, we proposed a speech support system using body-conducted speech recognition. This system retrieves speech from body-conducted sound via a transfer function, using recognition to select a sub-word sequence and its duration. In this study, we demonstrate the effectiveness of producing clear body-conducted speech using a linear predictive coefficient instead of a transfer function. We estimated interval information by heuristic method to divide body-conducted speech into syllables as in past study. In this study, we used continuous sub-word recognition automatically. To confirm the improvement in synthesized speech, a jury test and articulatory feature analysis were employed.
Journal
-
- Transactions of Japan Society of Kansei Engineering
-
Transactions of Japan Society of Kansei Engineering 15 (1), 127-134, 2016
Japan Society of Kansei Engineering
- Tweet
Details 詳細情報について
-
- CRID
- 1390282680304002816
-
- NII Article ID
- 130005128771
-
- ISSN
- 18845258
- 18840833
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed