Speech Libraries - Page 30

Unknown Detection Party

C++ 25Updated: 4 y ago License: Permissive (MIT)

useful for learning android audio system

C 25Updated: 3 y ago License: Permissive (Apache-2.0)

PyTorch implementation of Listen Attend and Spell Automatic Speech Recognition (ASR).

Shell 25Updated: 3 y ago License: Permissive (MIT)

The open source intelligent personal assistant

C 25Updated: 5 y ago License: Strong Copyleft (GPL-2.0)

Voice commands (command your PC with spoken commands)

Shell 25Updated: 4 y ago License: No License (No License)

A free, premium quality speech synthesis engine written completely in C.

C 25Updated: 3 y ago License: Permissive (MIT)

Tensorflow implementation of "FloWaveNet: A Generative Flow for Raw Audio"

Jupyter Notebook 25Updated: 3 y ago License: Permissive (MIT)

Converts SRT subtitle file to SSML file with speech durations

Python 25Updated: 2 y ago License: Permissive (MIT)

Pitch Controllable DDSP Vocoders

Python 25Updated: 1 y ago License: Permissive (MIT)

A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy audio signals in audio space for the first time.

Python 25Updated: 2 y ago License: No License (No License)

Python WebSocket server which converts input audio stream from microphone to text using Google speech to text

Python 24Updated: 4 y ago License: No License (No License)

Convert ppt to video with audio track, using text to speech synthesis

Python 24Updated: 4 y ago License: No License (No License)

5-class Korean speech emotion classifier

Python 24Updated: 4 y ago License: Permissive (MIT)

HAL-9000 Speech Simulator

Python 24Updated: 4 y ago License: Permissive (MIT)

Constrained Permutation Invariant Training, Speech Separation

Python 24Updated: 3 y ago License: No License (No License)

A simple GUI application to help record audio dictated from given text prompts, for use with training speech recognition.

Python 24Updated: 4 y ago License: Strong Copyleft (AGPL-3.0)

an tutorial implement of voice conversion using pytorch

Python 24Updated: 4 y ago License: No License (No License)

🦁 Nala is an agile open-source voice assistant framework (20+ actions).

Python 24Updated: 4 y ago License: Proprietary (Proprietary)

Speech recognition using Google Cloud Speech API

Python 24Updated: 4 y ago License: No License (No License)

Create a web-based intelligent personal assistant (IPA) in NodeJS using two Watson services: Natural Language Classifier (NLC) and Dialog. https://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/doc/nl-classifier/ www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/dialog.html

JavaScript 24Updated: 6 y ago License: Permissive (Apache-2.0)

Self-contained multilingual TTS speech synthesizer for Node.js in pure js

JavaScript 24Updated: 3 y ago License: Permissive (MIT)

Node module for voice commands using native, offline speech recognition.

C# 24Updated: 4 y ago License: Permissive (MIT)

RestSharp with Polly

C# 24Updated: 3 y ago License: No License (No License)

Web Browser Audio Detection/Speech Recording Events API

JavaScript 24Updated: 2 y ago License: Permissive (MIT)

Angular 5+ speech recognition service (based on browser implementation such as Chrome).

TypeScript 24Updated: 3 y ago License: Permissive (MIT)

the Tensorflow version of multi-speaker TTS training with feedback constraint

Python 24Updated: 4 y ago License: Permissive (MIT)

AI grand challenge 2020 Repo (Speech Recognition Track)

Python 24Updated: 4 y ago License: Permissive (MIT)

An extensible speech synthesis system, build with PyTorch and the original code is from r9y9's https://github.com/r9y9/nnmnkwii_gallery

Python 24Updated: 4 y ago License: No License (No License)

Add-ons for Home Assistant's Hass.IO

Shell 24Updated: 2 y ago License: Permissive (MIT)

Keyword Search Recipe for Subword ASR

Shell 24Updated: 4 y ago License: Permissive (MIT)

Convert text to audiable speech. Play it or save it to audio file.

Swift 24Updated: 4 y ago License: Strong Copyleft (GPL-3.0)

Few-Shot Keyword Spotting

Jupyter Notebook 24Updated: 3 y ago License: No License (No License)

Non-blocking Asterisk modules for accessing VoiceKit services for speech recognition and speech synthesis.

Shell 24Updated: 3 y ago License: No License (No License)

Official implementation of SpeechSplit2

Python 24Updated: 3 y ago License: No License (No License)

Speaker anonymization pipeline for hiding the identity of the speaker of a recording by changing the voice in it.

Python 24Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

Twitter Spaces Host and Speaker's Lounge

JavaScript 24Updated: 2 y ago License: Permissive (MIT)

Python 24Updated: 2 y ago License: No License (No License)

A virtual waifu that you can speak to through your mic and it'll speak back to you!

Python 24Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

Mass interaction physics library for Processing, including Audio and Haptic capabilities. Latest compiled release for Processing environment : https://github.com/mi-creative/miPhysics_Processing/releases/tag/2.0.0

Java 23Updated: 4 y ago License: Strong Copyleft (GPL-3.0)

Towards an end-to-end speech recognizer for Portuguese using deep neural networks

Python 23Updated: 4 y ago License: Permissive (MIT)

Some simple wrappers around eSpeak NG intended to make using this excellent TTS for waveform and IPA generation as convenient as possible.

Python 23Updated: 4 y ago License: Permissive (Apache-2.0)

Hybrid speech synthesiser

Python 23Updated: 4 y ago License: Permissive (Apache-2.0)

Tensorflow 2 implementation of Speech Separation Methods

Python 23Updated: 4 y ago License: No License (No License)

PAGAN: a phase-adapted GAN for speech enhancement

Python 23Updated: 4 y ago License: Permissive (MIT)

[KAIST CS420] Transfer Learning from Speaker Verification to Zero-Shot Multispeaker Korean Text-To-Speech Synthesis

Python 23Updated: 3 y ago License: No License (No License)

Properly handle position-dependent phones in a subword lexicon FST

Python 23Updated: 4 y ago License: Permissive (MIT)

Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling"

Python 23Updated: 4 y ago License: No License (No License)

声纹识别(Voiceprint Recognition, VPR)，也称为说话人识别(Speaker Recognition)，有两类，即说话人辨认(Speaker Identification)和说话人确认(Speaker Verification)

Python 23Updated: 3 y ago License: No License (No License)

In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.

Python 23Updated: 4 y ago License: Permissive (BSD-3-Clause)

A wavelet audio denoiser done in python

Python 23Updated: 4 y ago License: No License (No License)