Nearly defect-free F0 trajectory extraction for expressive speech modifications based on STRAIGHT
By Hideki Kawahara, A. de Cheveigné, Hideki Banno, Toru Takahashi, Toshio Irino. 2005
113 citations recorded by the source corpus.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Tomoki Toda
- Masanori Morise
- Hisashi Kawai
- Takuma Okamoto
- Kenji Ozawa
- Fumiya Yokomori
- Junichi Yamagishi
- Yoshinori Shiga
In Signal Processing
- Tomoki Toda
- Masanori Morise
- Kenji Ozawa
- Fumiya Yokomori
- Hisashi Kawai
- Takuma Okamoto
- Junichi Yamagishi
- Yoshinori Shiga
Citations in the corpus
- WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications (2016, methodology): “Legacy-STRAIGHT used nearly defect-free (NDF) F0 trajectory extraction [33], its most accurate F0 estimation algorithm.”
- Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems (2019, methodology): “Fundamental frequency fo, analyzed by an NDF algorithm [56] was used in all vocoders with VF [37, 50] and STRAIGHT.”
- STRAIGHT, exploitation of the other aspect of VOCODER: Perceptually isomorphic decomposition of speech sounds (2006, methodology): “In the current implementation, normalized autocorrelation based procedure was integrated with the previous instantaneous frequency based procedure to reduce F0 extraction errors further [4].”
- Improving FFTNet Vocoder with Noise Shaping and Subband Approaches (2018, methodology): “The fundamental frequency fo, analyzed by an NDF algorithm implemented in STRAIGHT [59], was used in all the vocoders.”
- Technical foundations of TANDEM-STRAIGHT, a speech analysis, modification and synthesis framework (2011, unknown): “The third integrates instantaneous frequency-based and autocorrelation-based methods with heavy post-processing (Kawahara et al 2005).”
- An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features (2018, methodology): “Fundamental frequency fo, analyzed by an NDF algorithm implemented in STRAIGHT [28], was used in all the vocoders.”
- Temporally variable multi-aspect N-way morphing based on interference-free speech representations (2013, background): “An integration variable ξ is a point on the time axis of A.”