Voice Conversion Using a Perceptual Criterion
In voice conversion (VC), it is highly desirable to obtain transformed speech signals that are perceptually close to a target speaker’s voice. To this end, a perceptually meaningful criterion where the human auditory system was taken into consideration in measuring the distances between the converte...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/8/2884 |
| _version_ | 1797570071473684480 |
|---|---|
| author | Ki-Seung Lee |
| author_facet | Ki-Seung Lee |
| author_sort | Ki-Seung Lee |
| collection | DOAJ |
| description | In voice conversion (VC), it is highly desirable to obtain transformed speech signals that are perceptually close to a target speaker’s voice. To this end, a perceptually meaningful criterion where the human auditory system was taken into consideration in measuring the distances between the converted and the target voices was adopted in the proposed VC scheme. The conversion rules for the features associated with the spectral envelope and the pitch modification factor were jointly constructed so that perceptual distance measurement was minimized. This minimization problem was solved using a deep neural network (DNN) framework where input features and target features were derived from source speech signals and time-aligned version of target speech signals, respectively. The validation tests were carried out for the CMU ARCTIC database to evaluate the effectiveness of the proposed method, especially in terms of perceptual quality. The experimental results showed that the proposed method yielded perceptually preferred results compared with independent conversion using conventional mean-square error (MSE) criterion. The maximum improvement in perceptual evaluation of speech quality (PESQ) was 0.312, compared with the conventional VC method. |
| first_indexed | 2024-03-10T20:19:52Z |
| format | Article |
| id | doaj.art-fb1f585af195451bbe205f19aedbe8d6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T20:19:52Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fb1f585af195451bbe205f19aedbe8d62023-11-19T22:19:47ZengMDPI AGApplied Sciences2076-34172020-04-01108288410.3390/app10082884Voice Conversion Using a Perceptual CriterionKi-Seung Lee0Department of Electronic Engineering, Konkuk University, 1 Hwayang-dong, Gwangjin-gu, Seoul 143-701, KoreaIn voice conversion (VC), it is highly desirable to obtain transformed speech signals that are perceptually close to a target speaker’s voice. To this end, a perceptually meaningful criterion where the human auditory system was taken into consideration in measuring the distances between the converted and the target voices was adopted in the proposed VC scheme. The conversion rules for the features associated with the spectral envelope and the pitch modification factor were jointly constructed so that perceptual distance measurement was minimized. This minimization problem was solved using a deep neural network (DNN) framework where input features and target features were derived from source speech signals and time-aligned version of target speech signals, respectively. The validation tests were carried out for the CMU ARCTIC database to evaluate the effectiveness of the proposed method, especially in terms of perceptual quality. The experimental results showed that the proposed method yielded perceptually preferred results compared with independent conversion using conventional mean-square error (MSE) criterion. The maximum improvement in perceptual evaluation of speech quality (PESQ) was 0.312, compared with the conventional VC method.https://www.mdpi.com/2076-3417/10/8/2884voice conversionjoint conversionperceptual distance measure |
| spellingShingle | Ki-Seung Lee Voice Conversion Using a Perceptual Criterion Applied Sciences voice conversion joint conversion perceptual distance measure |
| title | Voice Conversion Using a Perceptual Criterion |
| title_full | Voice Conversion Using a Perceptual Criterion |
| title_fullStr | Voice Conversion Using a Perceptual Criterion |
| title_full_unstemmed | Voice Conversion Using a Perceptual Criterion |
| title_short | Voice Conversion Using a Perceptual Criterion |
| title_sort | voice conversion using a perceptual criterion |
| topic | voice conversion joint conversion perceptual distance measure |
| url | https://www.mdpi.com/2076-3417/10/8/2884 |
| work_keys_str_mv | AT kiseunglee voiceconversionusingaperceptualcriterion |