TY - JOUR
T1 - Multilingual evaluation of voice disability index using pitch rate
AU - Shinohara, Shuji
AU - Omiya, Yasuhiro
AU - Nakamura, Mitsuteru
AU - Hagiwara, Naoki
AU - Higuchi, Masakazu
AU - Mitsuyoshi, Shunji
AU - Tokuno, Shinichi
N1 - Funding Information:
This research is (partially) supported by the Center of Innovation Program from the Japan Science and Technology Agency, JST. This work was supported by JSPS KAKENHI Grant Numbers JP16K01408 and JP15H03002.
PY - 2017
Y1 - 2017
N2 - We propose the use of the pitch rate of free-form speech recorded by smartphones as an index of voice disability. This research compares the effectiveness of pitch rate, jitter, shimmer, and harmonic-to-noise ratio (HNR) as indices of voice disability in English, German, and Japanese. Normally, the evaluation of these indices is performed using long-vowel sounds; however, this study included the recitation of a set passage, which is more similar to free-form speech. The results showed that for English, the jitter, shimmer, and HNR were very effective indices for long-vowel sounds, but the shimmer and HNR for read speech were considerably worse. Although the effectiveness of jitter as an index was maintained for read speech, the pitch rate was better in distinguishing between healthy individuals and patients with illnesses affecting their voice. The read speech results in German, Japanese, and English were similar, and the pitch rate showed the greatest efficiency for identification. Nevertheless, compared to English, the identification efficiency for the other two languages was lower.
AB - We propose the use of the pitch rate of free-form speech recorded by smartphones as an index of voice disability. This research compares the effectiveness of pitch rate, jitter, shimmer, and harmonic-to-noise ratio (HNR) as indices of voice disability in English, German, and Japanese. Normally, the evaluation of these indices is performed using long-vowel sounds; however, this study included the recitation of a set passage, which is more similar to free-form speech. The results showed that for English, the jitter, shimmer, and HNR were very effective indices for long-vowel sounds, but the shimmer and HNR for read speech were considerably worse. Although the effectiveness of jitter as an index was maintained for read speech, the pitch rate was better in distinguishing between healthy individuals and patients with illnesses affecting their voice. The read speech results in German, Japanese, and English were similar, and the pitch rate showed the greatest efficiency for identification. Nevertheless, compared to English, the identification efficiency for the other two languages was lower.
KW - Harmonic to noise ratio
KW - Jitter
KW - Multilingual evaluation
KW - Pitch detection ratio
KW - Read speech
KW - Shimmer
KW - Voice disability
UR - http://www.scopus.com/inward/record.url?scp=85048294344&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048294344&partnerID=8YFLogxK
U2 - 10.25046/aj020397
DO - 10.25046/aj020397
M3 - Article
AN - SCOPUS:85048294344
VL - 2
SP - 765
EP - 772
JO - Advances in Science, Technology and Engineering Systems
JF - Advances in Science, Technology and Engineering Systems
SN - 2415-6698
IS - 3
ER -