Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speech

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 147
  • Download : 0
Although recent neural text-to-speech (TTS) systems have achieved high-quality speech synthesis, there are cases where a TTS system generates low-quality speech, mainly caused by limited training data or information loss during knowledge distillation. Therefore, we propose a novel method to improve speech quality by training a TTS model under the supervision of perceptual loss, which measures the distance between the maximum possible speech quality score and the predicted one. We first pre-train a mean opinion score (MOS) prediction model and then train a TTS model to maximize the MOS of synthesized speech using the pre-trained MOS prediction model. The proposed method can be applied independently regardless of the TTS model architecture or the cause of speech quality degradation and efficiently without increasing the inference time or model complexity. The evaluation results for the MOS and phone error rate demonstrate that our proposed approach improves previous models in terms of both naturalness and intelligibility.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2022-05
Language
English
Article Type
Article
Citation

IEEE ACCESS, v.10, pp.52621 - 52629

ISSN
2169-3536
DOI
10.1109/ACCESS.2022.3175810
URI
http://hdl.handle.net/10203/296934
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0