TTS-Guided Training for Accent Conversion Without Parallel Data
Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many existing AC approaches rely on source-target parallel speech data during training or reference speech at run-time. We propose a no...
Main Authors: | Li, H. (Author), Tian, X. (Author), Wu, Z. (Author), Zhang, M. (Author), Zhou, Y. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
Subjects: | |
Online Access: | View Fulltext in Publisher View in Scopus |
Similar Items
-
Articulatory-based Speech Processing Methods for Foreign Accent Conversion
by: Felps, Daniel
Published: (2012) -
Accent labeling algorithm based on morphological rules and machine learning in English conversion system
by: Liu Xiaofeng, et al.
Published: (2021-07-01) -
Loss of regional accent after damage to the speech production network
by: Marcelo L Berthier, et al.
Published: (2015-11-01) -
Language beyond Words: The Neuroscience of Accent
Published: (2017) -
Nonnative-Accented Word Recognition: Children’s Use of Sentence Context
by: Miller, Katherine
Published: (2018)