.png){kind=icon}
.png){kind=icon}
Return
Do End-to-End TTS Systems Exploit Patterns in Speech?
.png){kind=icon}
PRE
AI
DOI：10.1007/978-981-95-4395-3_7.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
An end-to-end (e2e) text-to-speech (TTS) system is a deep architecture that learns to associate a text string with acoustic speech patterns from a dataset. It is expected that all aspects associated with speech production, such as phone duration, speaker characteristics, and intonation among other things are captured in the trained TTS model. Human speech is complex, involving smooth transitions between articulatory configurations (ACs). Due to anatomical constraints, some ACs are challenging to mimic or transition between. In this paper, we pose the question Do e2e-TTS systems benefit by the constraints imposed by human anatomy?. To answer this, we build systems using reverse text and reverse speech. Experiments demonstrate that e2e TTS systems are purely data-driven. Interestingly, the generated speech by reverse systems exhibits better fidelity, better perceptual intelligibility, and better naturalness.
Keywords:
TTS
reverse speech
end to endmodels
tokenization
Journal
P
IF:
0
Papers:
27
Citations:
0