← Search

Dang-Khoa Mac

2 accepted papers

2023

How to Push the Fastest Model 50x Faster: Streaming Non-Autoregressive Speech Synthesis on Resouce-Limited Devices

ICASSP 2023accepted

Minimizing the latency of the text-to-speech system on end-user resource-limited devices is one of the top demands of voice-based human-machine interaction applications. In this paper, the FastStreamSpeech model is proposed combining the advantages of the advanced approaches in neural-based speech s…

Cited by 0SourceScholar
2021

How to Make Text-to-Speech System Pronounce "Voldemort": an Experimental Approach of Foreign Word Phonemization in Vietnamese

ICASSP 2021accepted

Generating foreign words is one of the hardest tasks for any speech synthesis systems. This work deal with this problem in the case of Vietnamese, a low-resourced language, following an experimental approach. Base on a deep analysis of the usage of foreign words in Vietnamese, various types of pronu…

Cited by 0SourceScholar