Speech analysis/Synthesis based on a sinusoidal representation

By R. McAulay, Thomas F. Quatieri. 1986

How researchers see this paper

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

In Speech & Audio

Citations in the corpus

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications (2016, background): “Other speech synthesis systems have been proposed such as phase vocoder [6], PSOLA [7], and sinusoidal model [8], and high-quality speech synthesis remains a popular research topic.”
DDSP: Differentiable Digital Signal Processing (2020, background): “Source-ﬁlter/subtractive models are inspired by the human vocal tract and dynamically ﬁlter a harmonically rich source signal (Flanagan, 2013), while sinusoidal/additive models generate sound as the combination of a set of time-varying sine waves (McAulay & Quatieri, 1986; Serra & Smith, 1990).”
Wavenet Based Low Rate Speech Coding (2017, background): “The parameter set differs little for approaches based on a temporal perspective with glottal pulse trains [15, 16], and those based on a frequency-domain perspective with sinusoids [17, 18].”
Improving Opus Low Bit Rate Quality with Neural Speech Synthesis (2019, background): “Examples are linear predictive vocoders [1, 2] or sinusoidal coders [3, 4].”
Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis (2018, methodology): “Inspired by classical speech modeling methods [7, 8], we used a source”
Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations (2021, methodology): “Traditionally, this has been studied in the digital signal processing (DSP) field using fundamental methods such as sinusoidal modeling or linear predictive coding (LPC), and it is the analysis and synthesis framework that lies at the heart of those fundamental methods [26, 3].”
Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds (1999, methodology): “Various sophisticated methods have been proposed [18, 24, 19, 25], but their flexibility and resultant speech quality have been limited.”
Robust Low Rate Speech Coding Based on Cloned Networks and Wavenet (2020, methodology): “Alternative methods, such as sinusoidal coding [9, 10] and waveform interpolation [11], did not lead to signifant improvements in overall performance.”
Speech Emotion Recognition Using Fourier Parameters (2015, background): “In other words, a speech signal can be represented as the result of passing a glottal excitation waveform through a time-varying linear filter, which models the resonant characteristics of the vocal tract [17].”
Multi-Pitch Estimation (2009, unknown): “SOME APPLICATIONS 5 the pitch, sometimes referred to as time-scale modification [57, 58, 113, 114].”
A tutorial on onset detection in music signals (2005, methodology): “Sinusoidal models, such as " additive synthesis " [7], represent an audio signal as a sum of sinusoids with slowly varying parameters .”
Speech representation and transformation using adaptive interpolation of weighted spectrum: vocoder revisited (1997, background): “This equation is very close to t,he sinusoidal representation’s[4], but the procrdure to make me of this formulation is quite different.”
Error Evaluation of an F0-Adaptive Spectral Envelope Estimator in Robustness against the Additive Noise and F0 Error (2015, methodology): “Several types of speech synthesis technologies have been proposed such as PSOLA [1], sinusoidal model [2], and phase vocoder.”
A Review of Deep Learning Based Speech Synthesis (2019, methodology): “Other methods such as phase vocoder [36], PSOLA [18] and sinusoidal model [37] are also proposed.”
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions (2020, methodology): “Traditional vocoder approaches mostly involved sourcefilter model for the generation of speech parameters [9, 10, 11, 12].”
Quasi-Periodic Parallel WaveGAN Vocoder: A Non-autoregressive Pitch-dependent Dilated Convolution Model for Parametric Speech Generation (2020, methodology): “The conventional vocoders such as STRAIGHT [3] and WORLD (WD) [4] are usually designed on the basis of a source-filter model [5], which decomposes speech into spectral and prosodic acoustic features.”
CheapTrick, a spectral envelope estimator for high-quality speech synthesis (2015, background): “Sinusoidal models (McAulay and Quatieri, 1986) are also effective for high-quality speech synthesis, but it is difficult for them to achieve high-quality voice conversion.”
Techniques for Harmonic Sinusoidal Coding (1997, methodology): “To produce a continuous time domain waveform the IDFTs from adjacent frames are smoothly interpolated using a weighted overlap add [18] procedure.”