kaldi-asr / kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

deep-neural-networks deep-learning speech dnn pytorch recurrent-neural-networks lstm gru speech-recognition rnn kaldi rnn-model asr lstm-neural-networks multilayer-perceptron-network timit dnn-hmm

Updated Jun 11, 2020
Python

Kyubyong / tacotron

Star

A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

tensorflow speech tts speech-synthesis-model

Updated Mar 19, 2018
Python

readbeyond / aeneas

Star

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

Updated Jul 15, 2020
Python

r9y9 / wavenet_vocoder

Star

WaveNet vocoder

python speech pytorch speech-synthesis wavenet speech-processing wavenet-vocoder neural-vocoder

Updated Apr 1, 2020
Python

didi / delta

Star

DELTA is a deep learning based natural language and speech processing platform.

Updated Aug 21, 2020
Python

pndurette / gTTS

Star

Python library and CLI tool to interface with Google Translate's text-to-speech API

python text-to-speech speech tts gtts

Updated Aug 16, 2020
Python

julius-speech / julius

Star

Open-Source Large Vocabulary Continuous Speech Recognition Engine

recognition speech speech-recognition audio-processing

Updated Aug 13, 2020
C

pytorch / audio

Star

Data manipulation and transformation for audio signal processing, powered by PyTorch

audio python mp3 speech wav io

Updated Aug 20, 2020
Python

PaddlePaddle / DeepSpeech

Star

A PaddlePaddle implementation of DeepSpeech2 architecture for ASR.

speech speech-recognition speech-to-text deep-speech

Updated Jun 28, 2020
Python

Kyubyong / dc_tts

Star

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

speech tts speech-to-text

Updated Jun 7, 2018
Python

jarikomppa / soloud

Star

Open

more filters should be implemented

1

brightening-eyes commented Feb 20, 2018

hi,
as you know, in SoLoud, the number of filters are limited
we should implement more like different reverbs, fir and irr filters, (these could be used to implement HRTF support), Chorus, One Poll, One Zero, Pole Zero, Two Pole, Two Zero, etc
a library exists called stk under zlib license which already implemented these maybe we can implement some of these out

Seek performance

4

pykaldi / pykaldi

Star

A Python wrapper for Kaldi

python wrapper numpy speech feature-extraction speech-recognition kaldi language-model asr openfst clif

Updated Aug 17, 2020
Python

santi-pdp / segan

Star

Speech Enhancement Generative Adversarial Network in TensorFlow

deep-neural-networks deep-learning tensorflow speech gan generative-model generative-adversarial-networks

Updated May 26, 2020
Python

praat / praat

Star

Praat: Doing Phonetics By Computer

speech phonetics acoustics

Updated Aug 19, 2020
Objective-C

jtkim-kaist / VAD

Star

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

data speech dnn lstm speech-recognition attention vad voice-detection voice-activity-detection bdnn acam speech-activity-detection

Updated Jun 22, 2020
MATLAB

evancohen / sonus

Star

💬 /so.nus/ STT (speech to text) for Node with offline hotword detection

alexa node speech voice-recognition speech-recognition speech-to-text voice-control stt hotword-detection keyword-spotting

Updated Aug 8, 2020
JavaScript

MITESHPUTHRANNEU / Speech-Emotion-Analyzer

Star

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

data-science natural-language-processing deep-neural-networks deep-learning neural-network keras voice speech emotion python3 audio-files speech-recognition emotion-recognition natural-language-understanding speech-emotion-recognition

Updated Dec 7, 2018
Jupyter Notebook

lkuza2 / java-speech-api

Star

The J.A.R.V.I.S. Speech API is designed to be simple and efficient, using the speech engines created by Google to provide functionality for parts of the API. Essentially, it is an API written in Java, including a recognizer, synthesizer, and a microphone capture utility. The project uses Google services for the synthesizer and recognizer. While this requires an Internet connection, it provides a complete, modern, and fully functional speech API in Java.

java api google recognition speech speech-synthesis speech-recognition speech-to-text jarvis