There are 3 repositories under prosody topic.
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
INTERSPEECH 2023 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023 conference. Explore the latest advances in speech and language processing. Code included. Star the repository to support the advancement of speech technology!
feature extraction from speech signals
Helsinki Prosody Corpus and A System for Predicting Prosodic Prominence from Text
PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, INTERSPEECH 2021
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Tool(s) to help read Sanskrit (and other) metrical verse
Docker Jitsi Meet WebRTC conferencing system w/Prosody XMPP and s6 overlay
:key: Authentication hub for Nextcloud+JSXC→Prosody, ejabberd, saslauthd, Postfix
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Golang mod_http_upload_external server for Prosody and Ejabberd
PyTorch Implementation of Robust and fine-grained prosody control of end-to-end speech synthesis
Simple and extendable appserver for XMPP pushes (aka. XEP-0357)
Tool to analyze an audio corpora in terms of intonation, intensity, duration and voice quality
This is a setup for a Tor based mail hosting server
Install and maintain Prosody from offical repo with Ansible. Per default, this role also installs monit and munin-node to monitor Prosody. Contains tests for Travis CI and Vagrant.
Shanghainese TTS
Tools for analyzing the prosody of Ancient Greek poetry and prose.
Acoustic-prosodic entrainment measurement in spoken dialogue and approximation of the evolution of a speaker’s a/p features.
A workflow for acoustic analysis of speech prosody based on continuous measurements of periodic energy and F0 (requires Praat and R). ProPer analyses cover a wide range of prosodic phenomena, including pitch contours, prominence, speech-rate and syllabic structure. ProPer provides rich visual representations and quantification procedures for prosody in speech.
Prosody Docker image based on Alpine Linux
An MVP for a prosody visualizer to help English speakers compare their speech prosody (voice pitch and intensity) to that of a native speaker.
housekeeping script to clean up Prosodys env and Database
A minimal server that listens to the events sent by event_sync module for capturing meeting stats and store these stats to postgres DB.
Vector Quantized PPGs based Voice conversion