Flora Xue

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2020-97

May 29, 2020

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-97.pdf

Adaptive text-to-speech (TTS) system has a lot of interesting and useful applications, but most of the existing algorithms are designed for training and running the system in the cloud. This thesis proposes an adaptive TTS system designed for edge devices with a low computational cost based on generative flows. The system, which is only 7.2G MACs and 42x smaller than its baseline, has the potential to adapt and infer without exceeding the memory constraint and edge processor capacity. Despite its low-cost, the system can still adapt to a target speaker with the same similarity and no significant audio naturalness degradation as with baseline models.

Advisors: Kurt Keutzer and Joseph Gonzalez

---

BibTeX citation:

@mastersthesis{Xue:EECS-2020-97,
    Author= {Xue, Flora},
    Title= {Adaptive Text-to-Speech in Low Computational Resource Scenarios},
    School= {EECS Department, University of California, Berkeley},
    Year= {2020},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-97.html},
    Number= {UCB/EECS-2020-97},
    Abstract= {Adaptive text-to-speech (TTS) system has a lot of interesting and useful applications, but most of the existing algorithms are designed for training and running the system in the cloud. This thesis proposes an adaptive TTS system designed for edge devices with a low computational cost based on generative flows. The system, which is only 7.2G MACs and 42x smaller than its baseline, has the potential to adapt and infer without exceeding the memory constraint and edge processor capacity. Despite its low-cost, the system can still adapt to a target speaker with the same similarity and no significant audio naturalness degradation as with baseline models.},
}

EndNote citation:

%0 Thesis
%A Xue, Flora 
%T Adaptive Text-to-Speech in Low Computational Resource Scenarios
%I EECS Department, University of California, Berkeley
%D 2020
%8 May 29
%@ UCB/EECS-2020-97
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-97.html
%F Xue:EECS-2020-97