Wavelet-based voice morphing
This paper presents a new multi-scale voice morphing algorithm. This algorithm enables a user to transform one person's speech pattern into another person's pattern with distinct characteristics, giving it a new identity, while preserving the original content. The voice morphing algorithm...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Published: |
2004
|
| _version_ | 1826272575580274688 |
|---|---|
| author | Orphanidou, C Moroz, I Roberts, S |
| author_facet | Orphanidou, C Moroz, I Roberts, S |
| author_sort | Orphanidou, C |
| collection | OXFORD |
| description | This paper presents a new multi-scale voice morphing algorithm. This algorithm enables a user to transform one person's speech pattern into another person's pattern with distinct characteristics, giving it a new identity, while preserving the original content. The voice morphing algorithm performs the morphing at different subbands by using the theory of wavelets and models the spectral conversion using the theory of Radial Basis Function Neural Networks. The results obtained on the TIMIT speech database demonstrate effective transformation of the speaker identity. |
| first_indexed | 2024-03-06T22:14:43Z |
| format | Journal article |
| id | oxford-uuid:53000f3e-d18d-447a-89b0-b307ce0e9d2f |
| institution | University of Oxford |
| last_indexed | 2024-03-06T22:14:43Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | oxford-uuid:53000f3e-d18d-447a-89b0-b307ce0e9d2f2022-03-26T16:28:56ZWavelet-based voice morphingJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:53000f3e-d18d-447a-89b0-b307ce0e9d2fMathematical Institute - ePrints2004Orphanidou, CMoroz, IRoberts, SThis paper presents a new multi-scale voice morphing algorithm. This algorithm enables a user to transform one person's speech pattern into another person's pattern with distinct characteristics, giving it a new identity, while preserving the original content. The voice morphing algorithm performs the morphing at different subbands by using the theory of wavelets and models the spectral conversion using the theory of Radial Basis Function Neural Networks. The results obtained on the TIMIT speech database demonstrate effective transformation of the speaker identity. |
| spellingShingle | Orphanidou, C Moroz, I Roberts, S Wavelet-based voice morphing |
| title | Wavelet-based voice morphing |
| title_full | Wavelet-based voice morphing |
| title_fullStr | Wavelet-based voice morphing |
| title_full_unstemmed | Wavelet-based voice morphing |
| title_short | Wavelet-based voice morphing |
| title_sort | wavelet based voice morphing |
| work_keys_str_mv | AT orphanidouc waveletbasedvoicemorphing AT morozi waveletbasedvoicemorphing AT robertss waveletbasedvoicemorphing |