Figure 1 - uploaded by Hieu-Thi Luong
Content may be subject to copyright.
Download
View publication
2: Outline of the thesis.

2: Outline of the thesis.

Source publication
Figure 1.1: Human speech production system.
Figure 1.2: Outline of the thesis.
Figure 2.1: A conceptual representation of the conventional TTS pipeline.
Figure 2.3: Decision tree clustering and speaker adaptation for TTS.
+27 Figure 2.4: Speaker-adaptive TTS with speech-encoded speaker embedding.
Deep learning based voice cloning framework for a unified system of text-to-speech and voice conversion
Thesis
Full-text available
  • Sep 2020
Speech synthesis is the technology of generating speech from an input. While the term is commonly used to refer to text-to-speech (TTS), there are many types of speech synthesis systems which handle different input interfaces such as voice conversion (VC), which converts speech of a source speaker to the voice of a target, or video-to-speech, which...
Cite
Download full-text

Similar publications

Fig. 1. The proposed system comprises of a text encoder (T Enc), a...
Fig. 3. Cloning procedure with transcribed speech of a target speaker....
Fig. 4. Blueprint of text-speech multimodal system. The naming...
NAUTILUS: A Versatile Voice Cloning System
Article
Full-text available
  • Jan 2020
We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker. By using a multi-speaker speech corpus to train all requisite encoders and decoders in the initial training stage, our system can clone unseen voices using untr...
View
Fig. 1. Block diagram of Tacotron2 based reference baseline that has...
Fig. 5. Comparison of various trade-off parameter λ 0.2, 0.4, 0.6, 0.8...
Decoding Knowledge Transfer for Neural Text-to-Speech Training
Article
Full-text available
  • Apr 2022
Neural end-to-end text-to-speech (TTS) is superior to conventional statistical methods in many ways. However, the exposure bias problem, that arises from the mismatch between the training and inference process in autoregressive models, remains an issue. It often leads to performance degradation in face of out-of-domain test data. To address this pr...
View