Abstract
This article presents a new algorithm used in order to convert the speech of one speaker so that it sounds like that of another speaker. This algorithm flexibly converts voice quality using two major technical developments. Firstly, the modification of formant frequencies and spectral intensity using piecewise linear voice conversion rules. This enables the control of spectrum parameters in detail. The conversion rules are generated automatically for any pair of speakers. The reliability of the conversion rules is guaranteed because they are statistically generated using training data. Secondly, this algorithm provides the ability to produce speech with the desired formant structure by controlling formant frequencies, formant bandwidths and spectral intensity. Speech is iteratively modified in order to achieve the specified formant structure. Listening tests prove that the proposed algorithm converts speaker individuality while maintaining high speech quality.
| Original language | English |
|---|---|
| Pages (from-to) | 153-164 |
| Number of pages | 12 |
| Journal | Speech Communication |
| Volume | 16 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 1995 |
| Externally published | Yes |
Fingerprint
Keywords
- Formant frequency
- Listening test
- Piecewise linear
- Spectral intensity
- Spectrum tilt
- Voice conversion
ASJC Scopus subject areas
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Software
- Modelling and Simulation
- Linguistics and Language
- Communication
- Signal Processing
- Electrical and Electronic Engineering
- Experimental and Cognitive Psychology
Cite this
Voice conversion algorithm based on piecewise linear conversion rules of formant frequency and spectrum tilt. / Mizuno, Hideyuki; Abe, Masanobu.
In: Speech Communication, Vol. 16, No. 2, 1995, p. 153-164.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Voice conversion algorithm based on piecewise linear conversion rules of formant frequency and spectrum tilt
AU - Mizuno, Hideyuki
AU - Abe, Masanobu
PY - 1995
Y1 - 1995
N2 - This article presents a new algorithm used in order to convert the speech of one speaker so that it sounds like that of another speaker. This algorithm flexibly converts voice quality using two major technical developments. Firstly, the modification of formant frequencies and spectral intensity using piecewise linear voice conversion rules. This enables the control of spectrum parameters in detail. The conversion rules are generated automatically for any pair of speakers. The reliability of the conversion rules is guaranteed because they are statistically generated using training data. Secondly, this algorithm provides the ability to produce speech with the desired formant structure by controlling formant frequencies, formant bandwidths and spectral intensity. Speech is iteratively modified in order to achieve the specified formant structure. Listening tests prove that the proposed algorithm converts speaker individuality while maintaining high speech quality.
AB - This article presents a new algorithm used in order to convert the speech of one speaker so that it sounds like that of another speaker. This algorithm flexibly converts voice quality using two major technical developments. Firstly, the modification of formant frequencies and spectral intensity using piecewise linear voice conversion rules. This enables the control of spectrum parameters in detail. The conversion rules are generated automatically for any pair of speakers. The reliability of the conversion rules is guaranteed because they are statistically generated using training data. Secondly, this algorithm provides the ability to produce speech with the desired formant structure by controlling formant frequencies, formant bandwidths and spectral intensity. Speech is iteratively modified in order to achieve the specified formant structure. Listening tests prove that the proposed algorithm converts speaker individuality while maintaining high speech quality.
KW - Formant frequency
KW - Listening test
KW - Piecewise linear
KW - Spectral intensity
KW - Spectrum tilt
KW - Voice conversion
UR - http://www.scopus.com/inward/record.url?scp=0029256372&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029256372&partnerID=8YFLogxK
U2 - 10.1016/0167-6393(94)00052-C
DO - 10.1016/0167-6393(94)00052-C
M3 - Article
AN - SCOPUS:0029256372
VL - 16
SP - 153
EP - 164
JO - Speech Communication
JF - Speech Communication
SN - 0167-6393
IS - 2
ER -