A comparison between STRAIGHT, glottal, and sinusoidal vocoding in statistical parametric speech synthesis

TY - JOUR

T1 - A comparison between STRAIGHT, glottal, and sinusoidal vocoding in statistical parametric speech synthesis

AU - Airaksinen, Manu

AU - Juvela, Lauri

AU - Bollepalli, Bajibabu

AU - Yamagishi, Junichi

AU - Alku, Paavo

PY - 2018/9

Y1 - 2018/9

N2 - A vocoder is used to express a speech waveform with a controllable parametric representation that can be converted back into a speech waveform. Vocoders representing their main categories (mixed excitation, glottal, sinusoidal vocoders) were compared in this study with formal and crowd-sourced listening tests. Vocoder quality was measured within the context of analysis-synthesis as well as text-to-speech (TTS) synthesis in a modern statistical parametric speech synthesis framework. Furthermore, the TTS experiments were divided into synthesis with vocoder-specific features and synthesis with a shared envelope model, where the waveform generation method of the vocoders is mainly responsible for the quality differences. Finally, all of the tests included four distinct voices as a way to investigate the effect of different speakers on the synthesized speech quality. The obtained results suggest that the choice of the voice has a profound impact on the overall quality of the vocoder-generated speech, and the best vocoder for each voice can vary case by case. The single best-rated TTS system was obtained with the glottal vocoder GlottDNN using a male voice with low expressiveness. However, the results indicate that the sinusoidal vocoder PML (pulse model in log-domain) has the best overall performance across the performed tests. Finally, when controlling for the spectral models of the vocoders, the observed differences are similar to the baseline results. This indicates that the waveform generation method of a vocoder is essential for quality improvements.

AB - A vocoder is used to express a speech waveform with a controllable parametric representation that can be converted back into a speech waveform. Vocoders representing their main categories (mixed excitation, glottal, sinusoidal vocoders) were compared in this study with formal and crowd-sourced listening tests. Vocoder quality was measured within the context of analysis-synthesis as well as text-to-speech (TTS) synthesis in a modern statistical parametric speech synthesis framework. Furthermore, the TTS experiments were divided into synthesis with vocoder-specific features and synthesis with a shared envelope model, where the waveform generation method of the vocoders is mainly responsible for the quality differences. Finally, all of the tests included four distinct voices as a way to investigate the effect of different speakers on the synthesized speech quality. The obtained results suggest that the choice of the voice has a profound impact on the overall quality of the vocoder-generated speech, and the best vocoder for each voice can vary case by case. The single best-rated TTS system was obtained with the glottal vocoder GlottDNN using a male voice with low expressiveness. However, the results indicate that the sinusoidal vocoder PML (pulse model in log-domain) has the best overall performance across the performed tests. Finally, when controlling for the spectral models of the vocoders, the observed differences are similar to the baseline results. This indicates that the waveform generation method of a vocoder is essential for quality improvements.

KW - Acoustics

KW - Predictive models

KW - Production

KW - Speech synthesis

KW - statistical parametric speech synthesis

KW - Transfer functions

KW - vocoder

KW - Vocoders

UR - http://www.scopus.com/inward/record.url?scp=85046811905&partnerID=8YFLogxK

U2 - 10.1109/TASLP.2018.2835720

DO - 10.1109/TASLP.2018.2835720

M3 - Article

VL - 26

SP - 1658

EP - 1670

JO - IEEE/ACM Transactions on Audio, Speech, and Language Processing

JF - IEEE/ACM Transactions on Audio, Speech, and Language Processing

SN - 2329-9290

IS - 9

ER -