CheapTrick, a spectral envelope estimator for high-quality speech synthesis

Morise, Masanori

doi:10.1016/j.specom.2014.09.003

Cited by 77 publications

(52 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The subjective evaluation has already been carried out, and its results suggested that CheapTrick achieved the best performance [17]. The results in this paper corroborated that CheapTrick was the best algorithm.…”

Section: Discussionsupporting

confidence: 71%

“…The results of subjective evaluation demonstrated that CheapTrick was superior to the conventional algorithms in terms of the sound quality of synthesized speech and robustness of the temporal F0 change [17]. On the other hand, since the real speech contains additive noise, the noise robustness must be verified.…”

Section: Discussionmentioning

confidence: 99%

“…1, CheapTrick consists of three steps: F0-adaptive windowing, smoothing of the power spectrum, and a liftering processing for smoothing and spectral recovery. Since the algorithm was described in detail in another paper [17], this paper explains its outline.…”

Section: The Algorithmmentioning

confidence: 99%

“…Since the proposed aperiodicity estimator requires an accurate spectral envelope, the performance of the spectral envelope must be estimated. This study is intended to evaluate the latest version of the spectral envelope estimator, named CheapTrick [17], from two objective aspects. In this paper, the robustness of the additive noise is evaluated.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error

Morise

2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper describes an evaluation of a temporally stable spectral envelope estimator proposed in our past research. The past research demonstrated that the proposed algorithm can synthesize speech that is as natural as the input speech. This paper focuses on an objective comparison, in which the proposed algorithm is compared with two modern estimation algorithms in terms of estimation performance and temporal stability. The results show that the proposed algorithm is superior to the others in both aspects. key words: speech analysis, spectral envelope, F0-adaptive analysis, timevarying component

show abstract

Section: Discussionsupporting

confidence: 71%

Section: Discussionmentioning

confidence: 99%

Section: The Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error

Morise

2015

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, the F0 contour is estimated with DIO [14], [15]. Second, the spectral envelope is estimated with CheapTrick [16], [18], which uses not only the waveform but also the F0 information. Third, the excitation signal is estimated with PLAT-INUM and used as an aperiodic parameter [17].…”

Section: Introductionmentioning

confidence: 99%

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications

Morise

Yokomori

Ozawa

2016

IEICE Trans. Inf. & Syst.

Self Cite

992

597

View full text Add to dashboard Cite

SUMMARYA vocoder-based speech synthesis system, named WORLD, was developed in an effort to improve the sound quality of realtime applications using speech. Speech analysis, manipulation, and synthesis on the basis of vocoders are used in various kinds of speech research. Although several high-quality speech synthesis systems have been developed, real-time processing has been difficult with them because of their high computational costs. This new speech synthesis system has not only sound quality but also quick processing. It consists of three analysis algorithms and one synthesis algorithm proposed in our previous research. The effectiveness of the system was evaluated by comparing its output with against natural speech including consonants. Its processing speed was also compared with those of conventional systems. The results showed that WORLD was superior to the other systems in terms of both sound quality and processing speed. In particular, it was over ten times faster than the conventional systems, and the real time factor (RTF) indicated that it was fast enough for real-time processing.

show abstract

A CycleGAN-Based Method for Translating Recordings of Interjections

Polianskaya,

Volkova

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

CheapTrick, a spectral envelope estimator for high-quality speech synthesis

Cited by 77 publications

References 20 publications

Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error

Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications

A CycleGAN-Based Method for Translating Recordings of Interjections

Contact Info

Product

Resources

About