Tandem-STRAIGHT: A temporally stable power spectral representation for periodic signals and applications to interference-free spectrum, F0, and aperiodicity estimation

By Hideki Kawahara, Masanori Morise, Toru Takahashi, Ryuichi Nisimura, Toshio Irino, Hideki Banno. 2008

391 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Signal Processing

Citations in the corpus

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications (2016, methodology): “TANDEM-STRAIGHT [12], [13] is supposed to be a sim-pliﬁed version that outputs almost all the same parameters as STRAIGHT.”
An investigation of multi-speaker training for wavenet vocoder (2017, methodology): “The second approach, parametric approach, is a technique to generate a synthesized speech by utilizing acoustic features and vocoder frameworks which represent physical characteristics of human speech production [3, 4, 5, 6, 7, 8, 9, 10].”
Vocaine the vocoder and applications in speech synthesis (2015, background): “The two most notable contributions here are STRAIGHT [14, 15] and AhoCoder [16] which is an STC/HNM variant.”
CheapTrick, a spectral envelope estimator for high-quality speech synthesis (2015, methodology): “The spectral recovery based on consistent sampling has been carried out on the frequency domain in the TANDEM-STRAIGHT (Kawahara et al., 2008) as follows.”
Modeling and Transforming Speech Using Variational Autoencoders (2016, methodology): “The STRAIGHT vocoder [16] allows decomposing a speech signal into F0, and a harmonic and aperiodic spectral envelope.”
Excitation source analysis for high-quality speech manipulation systems based on an interference-free representation of group delay with minimum phase response compensation (2014, methodology): “Source ﬁlter models provide a basis for VOCODER [12], LPC [13, 14], Cepstrum-based models [15, 16, 17] and STRAIGHT 1 [1, 2].”
PLATINUM: A method to extract excitation signals for voice synthesis system (2012, methodology): “The STRAIGHT [7] and TANDEM-STRAIGHT [8] have been proposed to solve this problem.”
Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “of TTS techniques from the formant-based methods [92, 97, 105, 106, 179, 224] to the unit selection-based waveform cascade methods [6, 24, 36, 59, 80, 143, 144], and to the hidden Markov model (HMM)-based statistical parametric speech synthesis (SPSS) methods [26, 94, 149, 178, 210, 241, 249, 250].”
Unsupervised Speech Decomposition via Triple Information Bottleneck (2020, methodology): “CDVAE-VC (Huang et al., 2018) uses two VAEs working on different speech features, one on STRAIGHT spectra (Kawahara et al., 2008), and one on mel-cepstral coeffcients (MCCs), and encourages that the latent representation can reconstruct both features well.”
Technical foundations of TANDEM-STRAIGHT, a speech analysis, modification and synthesis framework (2011, methodology): “The original STRAIGHT (legacy-STRAIGHT) was used for a decade and was superseded by TANDEM-STRAIGHT (Kawahara et al 2008), a complete reformulation and reengineering based on the same underlying concept.”
Pre-Trained Text Embeddings for Enhanced Text-to-Speech Synthesis (2019, background): “The waveform synthesis module is also a neural network [12–16] which converts a given sequence of acoustic features into a waveform signal, avoiding a signal processing based vocoder [17, 18] that may degrade the quality of synthesized speech due to simplifying assumptions about human speech generat”
Temporally variable multi-aspect N-way morphing based on interference-free speech representations (2013, methodology): “Let introduce TANDEM-STRAIGHT and representations first.”
v.morish'09: A Morphing-Based Singing Design Interface for Vocal Melodies (2009, methodology): “TANDEM-STRAIGHT [6] produces the same results that STRAIGHT does, only much more quickly.”
Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error (2015, methodology): “2015EDL8015 We have proposed a new speech analysis, manipulation, and synthesis framework [5] and several algorithms for spectral envelope estimation.”
A spectral envelope estimation method based on F0-adaptive multi-frame integration analysis (2012, methodology): “The envelope estimation accuracies obtained using our proposed method are sometimes better than those obtained using STRAIGHT and TANDEM-STRAIGHT.”
Vocal Manipulation Based on Pitch Transcription and Its Application to Interactive Entertainment for Karaoke (2011, positive): “TANDEM-STRAIGHT [ 12 ], which is an improved vocoder, can synthesize the voice that sounds as natural as the input voice, and manipulate the pitch Vocal Manipulation Based on Pitch Transcription 55”