All Projects → chdh → klatt-syn

chdh / klatt-syn

Licence: MIT license
Klatt formant synthesizer

Programming Languages

typescript
32286 projects

Projects that are alternatives of or similar to klatt-syn

TensorVox
Desktop application for neural speech synthesis written in C++
Stars: ✭ 140 (+677.78%)
Mutual labels:  speech-synthesis, voice-synthesis
spokestack-android
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: ✭ 52 (+188.89%)
Mutual labels:  speech-synthesis, voice-synthesis
spokestack-ios
Spokestack: give your iOS app a voice interface!
Stars: ✭ 27 (+50%)
Mutual labels:  speech-synthesis, voice-synthesis
Sinsy-NG
(discontinued) 🎵The Formant-Based All Language Singing Voice Syntheis System: Sinsy-NG
Stars: ✭ 15 (-16.67%)
Mutual labels:  speech-synthesis, formant
open-speech-corpora
💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
Stars: ✭ 841 (+4572.22%)
Mutual labels:  speech-synthesis
AmazonSpeechTranslator
End-to-end Solution for Speech Recognition, Text Translation, and Text-to-Speech for iOS using Amazon Translate and Amazon Polly as AWS Machine Learning managed services.
Stars: ✭ 50 (+177.78%)
Mutual labels:  speech-synthesis
speechrec
a simple speech recognition app using the Web Speech API Interfaces
Stars: ✭ 18 (+0%)
Mutual labels:  speech-synthesis
Cross-Speaker-Emotion-Transfer
PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Stars: ✭ 107 (+494.44%)
Mutual labels:  speech-synthesis
ppg-vc
PPG-Based Voice Conversion
Stars: ✭ 154 (+755.56%)
Mutual labels:  speech-synthesis
WaveGrad2
PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
Stars: ✭ 55 (+205.56%)
Mutual labels:  speech-synthesis
AdaSpeech
AdaSpeech: Adaptive Text to Speech for Custom Voice
Stars: ✭ 108 (+500%)
Mutual labels:  speech-synthesis
JSpeak
A Text to Speech Reader Front-end that Reads from the Clipboard and with Exceptionable Features
Stars: ✭ 16 (-11.11%)
Mutual labels:  voice-synthesis
Speech-Backbones
This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.
Stars: ✭ 205 (+1038.89%)
Mutual labels:  speech-synthesis
few-shot-transformer-tts
Byte-based multilingual transformer TTS for low-resource/few-shot language adaptation.
Stars: ✭ 60 (+233.33%)
Mutual labels:  speech-synthesis
sova-tts-tps
NLP-preprocessor for the SOVA-TTS project
Stars: ✭ 44 (+144.44%)
Mutual labels:  speech-synthesis
MediumVC
Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features
Stars: ✭ 46 (+155.56%)
Mutual labels:  speech-synthesis
Daft-Exprt
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Stars: ✭ 41 (+127.78%)
Mutual labels:  speech-synthesis
QPPWG
Quasi-Periodic Parallel WaveGAN Pytorch implementation
Stars: ✭ 41 (+127.78%)
Mutual labels:  speech-synthesis
deep-learning-german-tts
Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling.
Stars: ✭ 268 (+1388.89%)
Mutual labels:  speech-synthesis
VAENAR-TTS
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
Stars: ✭ 66 (+266.67%)
Mutual labels:  speech-synthesis

KlattSyn - Klatt Formant Synthesizer

This is a redevelopment of the classic Klatt cascade-parallel formant synthesizer. The program code is written in TypeScript, which is compiled to JavaScript. It can run within a web browser or with Node.

This implementation of a Klatt synthesizer has been developed by Christian d'Heureuse in 2019 and is based on the following documents and source code:

Online demo: www.source-code.biz/klattSyn
NPM package: klatt-syn
GUI application: github.com/chdh/klatt-syn-app

A note on amplitudes

The meaning of amplitude parameters has changed in this implementation of the Klatt synthesizer.

Amplitude values in dB are always relative. In this implementation, we use positive dB values to amplify and negative dB values to attenuate a signal. 0 is used to pass a signal unchanged. -99 is used to mute a signal.

The original Klatt synthesizer used dB values in the range 0 to 87 for amplitude parameters. 0 was used to mute a signal. 57 was used to pass a signal unchanged.

Klatt (1980) states: "The amplitudes of the formant peaks generated by the parallel vocal tract model have been constrained such that, if A1 to A5 are all set to 60 dB, the transfer function will approximate that found in the cascade model." This is no longer the case.

The following table can be used to pragmatically map old values to new values for amplitude parameters in dB:

Old dB New dB
87 30
57 0
27 -30
0 -99

In addition, most amplitude parameter values where internally adjusted in the old source code. To find the corresponding new value, An adjustment value must be subtracted.

Old symbol Linear factor Adjustment dB Parameter
AP 0.05 -26.0 Aspiration amplitude
AF 0.25 -12.0 Frication amplitude
AB 0.05 -26.0 Parallel bypass amplitude
A1 0.4 -8.0 Parallel formant 1 amplitude (L1)
A2 0.15 -16.5 Parallel formant 2 amplitude (L2)
A3 0.06 -24.4 Parallel formant 3 amplitude (L3)
A4 0.04 -28.0 Parallel formant 4 amplitude (L4)
A5 0.022 -33.2 Parallel formant 5 amplitude (L5)
A6 0.03 -30.5 Parallel formant 6 amplitude (L6)
AN 0.6 -4.4 Parallel nasal amplitude
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].