Software for a cascade/parallel formant synthesizer

By D. Klatt. 1980

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

Jukebox: A Generative Model for Music (2020, background): “Many text-to-speech (TTS) systems rely on highly engineered features (Klatt, 1980), carefully curated sound segments (Hunt & Black, 1996), statistical parametric modeling (Zen et al.”
A Survey on Neural Speech Synthesis (2021, methodology): “The early computer-based speech synthesis methods include articulatory synthesis [52, 294], formant synthesis [293, 5, 167, 168], and concatenative synthesis [247, 235, 291, 124, 26].”
TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese (2020, methodology): “Several acoustic models have been proposed such as the classical formant model [7], Linear Prediction Coefficients (LPC) model, the Pitch Synchronous Overlap and Add (PSOLA) models [8] widely used in TTS engines like Microsoft Speech API.”
Lexical activation (and other factors) can mediate compensation for coarticulation (2003, methodology): “Each syllable consisted of a naturally produced initial CV, followed by one of two fricatives (/s/ or /S/) that were created using a version of the Klatt (1980) synthesizer. Synthesis parameters are listed in the Appendix of Pitt and McQueen (1998). Each fricative was approximately 170ms long, and t”
Processing dependencies between segmental and suprasegmental features in Mandarin Chinese (2008, unknown): “Eight syllables were generated using a Klatt cascade/parallel formant synthesiser (Klatt, 1980; Klatt & Klatt, 1990).”
Thinking the voice: neural correlates of voice perception. (2004, background): “Formants correspond to the frequencies that are amplified by supra-laryngeal filtering and convey important phonetic information: most voiced phonemes can be approximated well by synthesizing sounds with energy at formant frequencies [ 13 ].”
The role of voice quality in communicating emotion, mood and attitude (2003, background): “It tends to be taken as axiomatic that creaky voice signals boredom for speakers of English (see Laver, 1980). In the present experiment, high response rates were achieved by the lax–creaky stimulus, which combines features of creaky and breathy voice. It is worth noting (Figs. 2 and 3) that this st”
A Review of Deep Learning Based Speech Synthesis (2019, methodology): “To address this problem, in 1980, Klatt’s serial/parallel formant synthesizer [17] was introduced.”
The phonetics of register in Takhian Thong Chong (2009, background): “Since radiation impedance is approximately proportional to frequency, the wide-band spectral slope is approximately -6 dB/octave for modal phonation ( Klatt, 1980; Pennington, 2005).”
Spoofing and countermeasures for speaker verification: A survey (2015, background): “In the early 1970s, the speech waveform generation component used very low dimensional acoustic parameters for each phoneme, such as formants, corresponding to vocal tract resonances with hand-crafted acoustic rules (Klatt, 1980).”
Speech Synthesis Based on Hidden Markov Models (2013, unknown): “In the early 1970s, the speech waveform generation component used very lowdimensional acoustic parameters for each phoneme, such as formants, corresponding to vocal tract resonances [2].”
An Adaptive Bias in the Perception of Looming Auditory Motion (2001, methodology): “The vowel sound was produced with a Klatt synthesizer (Klatt, 1980) and had a fundamental frequency of 100 Hz and formants at 450 Hz, 1450 Hz, and 2450 Hz.”
Effects of phase on the perception of intervocalic stop consonants (1997, methodology): “They generated the vowels using additive sine-wave synthesis based Ž .on Klatt 1980 cascade synthesizer and discovered that mistuning of only 1–2 Hz in harmonics close to F1 caused a lowering of the phoneme boundary in a Ž .categorization task.”
A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI (2023, unknown): “, formant synthesis [40, 41, 95] and concatenative synthesis [29, 69, 75]), statistical parametric speech synthesis (SPSS)-based methods [115, 116, 133], and neural network-based stage [122, 135, 136].”