.png){kind=icon}
返回
Variable-Length Speaker Conditioning in Flow-Based Text-to-Speech
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2024.3377588.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this letter, we propose a novel speaker conditioning technique that leverages a variable-length reference embedding sequence for flow-based text-to-speech (TTS) architecture in the context of zero-shot multi-speaker text-to-speech (ZSM-TTS). Unlike conventional ZSM-TTS methods, which usually rely on a single fixed-dimensional vector to represent the entire reference speech, our approach aims to extract variable-length embedding sequence for a more flexible and efficient conditioning. We enhance the current affine coupling function in flow-based TTS architecture by introducing an attentive speaker conditioning. This allows a local variation of the speaker conditioning. Our experiments demonstrate the effectiveness of the proposed method, highlighting improvements in terms of speaker similarity, speech naturalness, and speech intelligibility compared to the baseline methods.
Keyword:
Speech synthesis
variable-length reference embedding sequence
zero-shot multi-speaker text-to-speech
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
Evidence for a Relative Vitamin B6 Deficiency in Pregnancy and Some Disease States妊娠及某些疾病状态下相对维生素B6缺乏的证据
PREAI
分享收藏Mechanical Behavior of L-Shaped Concrete Filled Steel Tubular Columns under Axial Compression轴压下L形钢管混凝土柱的力学行为
OAAI
OAAI分享收藏分享收藏SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems
PREAI
分享收藏分享收藏
查看更多内容