entn-at Goto Github PK
Name: Ewald Enzinger
Type: User
Bio: Ph.D. EE (UNSW Sydney). ML, speaker recognition, speech recognition, speech synthesis, forensic voice comparison
Twitter: entn_at
Location: Portland, Oregon
Blog: https://entn.at/
Name: Ewald Enzinger
Type: User
Bio: Ph.D. EE (UNSW Sydney). ML, speaker recognition, speech recognition, speech synthesis, forensic voice comparison
Twitter: entn_at
Location: Portland, Oregon
Blog: https://entn.at/
A pytorch wrapper for LF-MMI training and parallel training in Kaldi
Probabilistic Linear Discriminant Analysis Model, written in Python.
Move Kaldi to mobile devices
Small language toolkit for creation, interpolation and pruning of ARPA language models
On-device wake word detection engine powered by deep learning.
Porcupine Hotword detection for the Raspberry Pi Zero
PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative Text-to-Speech
Phonetically-Oriented Word Error Rate
A diffusion-based cross-lingual voice conversion model, as my bachelor's thesis
PPG-Based Voice Conversion
An implementation of voice conversion system utilizing phonetic posteriorgrams
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
PPSpeech: Phrase based Parallel End-to-End TTS System
A python library for working with praat, textgrids, time aligned audio transcripts, and audio files. It is primarily used for extracting features from and making manipulations on audio files given hierarchical time-aligned transcriptions (utterance > word > syllable > phone, etc).
Corpus preprocessing
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
Speech Model Pre-training for End-to-End Spoken Language Understanding
Automatically exported from code.google.com/p/prism-set
Probabilistic PHOC
Uncertainty-aware Face Representation and Recognition
This repositoty [contains / will contain] Python code associated with our Oddyssey paper [put arXiv link here].
PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline
CURRENNNT codes and scripts
This repository contains the scripts to use CURRENNT
PronouncUR: An Urdu Pronunciation Lexicon Generator
Lexicon of frame files used by Propbank annotation. A searchable, readable version of these files is stored at http://verbs.colorado.edu/propbank/framesets-english-aliases/
The official released annotations, both in .prop pointer format and as conll files. Does not contain the source texts
MInf project exploring the use of prosodic information in language identification from speech, using the x-vector architecture in Kaldi, on the GlobalPhone dataset.
Helsinki Prosody Corpus and System for Predicting Prosodic Prominence from Text
This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems (https://arxiv.org/abs/2104.07777)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.