.png){kind=icon}
返回
TTS-Guided Training for Accent Conversion Without Parallel Data
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2023.3270079.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 novel accent conversion framework without the need for either parallel data or reference speech. Specifically, a text-to-speech (TTS) system is first pretrained with target-accented speech data. This TTS model and its hidden representations are expected to be associated only with the target accent. Then, a speech encoder is trained to convert the accent of the speech under the supervision of the pretrained TTS model. In doing so, the source-accented speech and its corresponding transcription are forwarded to the speech encoder and the pretrained TTS, respectively. The output of the speech encoder is optimized to be the same as the text embedding in the TTS system. At run-time, the speech encoder is combined with the pretrained speech decoder to convert the source-accented speech toward the target. In the experiments, we converted English with two source accents (Chinese/Indian) to the target accent (American/British/Canadian). Both objective metrics and subjective listening tests successfully validate that the proposed approach generates speech samples that are close to the target accent with high speech quality.
Keyword:
Acoustics
Training
Decoding
Feature extraction
Data models
Phonetics
Error analysis
Accent conversion (AC)
text-to-speech (TTS)
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Coccolith and Silicoflagellate Stratigraphy near Antarctica, Deep Sea Drilling Project, Leg 28南极洲附近的颗石藻和硅鞭藻地层学，深海钻探计划，第28航次OAAI
OAAI分享收藏The shadow economy in three Mediterranean countries: France, Spain and Greece. A MIMIC approach
PREAI
分享收藏FOREIGN ACCENT, COMPREHENSIBILITY, AND INTELLIGIBILITY IN THE SPEECH OF 2ND-LANGUAGE LEARNERS.png)
LANGUAGE LEARNING
LANGUAGE LEARNINGIF4.2
PREAI
分享收藏Ultrastructural analysis of the differentiation process of secondary xylem vessel element in Populus deltoides对Populus deltoides次生木质部导管分子分化过程的超微结构分析
PREAI
分享收藏分享收藏
查看更多内容