Alexandria Library

A curated collection of awesome articles

Here are some ressources related to Speech, Synthesis, Recognition. Hoping you will find learning material, alternative tools or just some interesting stuff.

Home > Programming, Machine Learning, Quan... > Machine Learning, Deep Learning, Ne... > NLP, Summarization, Machine Learnin... > Speech, Synthesis, Recognition

Articles

NaturalSpeech 2: Zero-shot speech and singing synthesizers

See discussion (120 comments, 235 points) - Archive

Universal Speech Model

See discussion (198 comments, 542 points) - Archive

Data2vec 2.0: Highly efficient self-supervised learning for vision, speech, text

See discussion (20 comments, 150 points) - Archive

Whisper – open source speech recognition by OpenAI

See discussion (481 comments, 1705 points) - Archive

NaturalSpeech: End-to-end text to speech synthesis with human-level quality

See discussion (149 comments, 377 points) - Archive

Meta AI: Fist high-performance self-supervised algorithm for multiple modalities

See discussion (56 comments, 89 points) - Archive

SoundStream: An End-to-End Neural Audio Codec

See discussion (103 comments, 286 points) - Archive

Wav2vec Overview: Semi and Unsupervised Speech Recognition

See discussion (22 comments, 162 points) - Archive

High-performance speech recognition with no supervision at all

See discussion (62 comments, 212 points) - Archive

Building an end-to-end Speech Recognition model in PyTorch

See discussion (33 comments, 288 points) - Archive

Towards an ImageNet Moment for Speech-to-Text

See discussion (10 comments, 86 points) - Archive

Pitch Detection with Convolutional Networks

See discussion (27 comments, 83 points) - Archive

Online speech recognition with wav2letter anywhere

See discussion (63 comments, 234 points) - Archive

AI Clones Your Voice After Listening for 5 Seconds (2018)

See discussion (319 comments, 911 points) - Archive

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

See discussion (11 comments, 86 points) - Archive

A 2019 Guide for Automatic Speech Recognition

See discussion (36 comments, 117 points) - Archive

A 2019 Guide to Speech Synthesis with Deep Learning

See discussion (20 comments, 139 points) - Archive

Translatotron: An End-to-End Speech-to-Speech Translation Model

See discussion (39 comments, 121 points) - Archive

Tacotron 2: Generating Human-Like Speech from Text

See discussion (54 comments, 290 points) - Archive

Speech Recognition Is Not Solved

See discussion (201 comments, 435 points) - Archive

Real-Time Recognition of Handwritten Chinese Characters

See discussion (42 comments, 115 points) - Archive

Deep Learning for Siri’s Voice

See discussion (90 comments, 234 points) - Archive

Conversational Speech Recognition System [pdf]

See discussion (11 comments, 82 points) - Archive

Generate your own sounds with NSynth

See discussion (30 comments, 147 points) - Archive

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

See discussion (84 comments, 339 points) - Archive

Audio texture synthesis and style transfer

See discussion (2 comments, 85 points) - Archive

Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

See discussion (42 comments, 172 points) - Archive

Deep Learning ‘ahem’ detector

See discussion (53 comments, 137 points) - Archive

Deep Speech 2: End-To-End Speech Recognition in English and Mandarin

See discussion (19 comments, 105 points) - Archive

Program Synthesis Demo

See discussion (19 comments, 126 points) - Archive

Federated finetuning of Whisper on Raspberry Pi 5

See discussion (20 comments, 90 points) - Archive

StyleTTS2 – open-source Eleven-Labs-quality Text To Speech

See discussion (234 comments, 725 points) - Archive

TuneNN: A transformer-based network model for pitch detection

See discussion (39 comments, 108 points) - Archive

BASE TTS: The largest text-to-speech model to-date

See discussion (78 comments, 200 points) - Archive

Hybrid-Net: Real-time audio source separation, generate lyrics, chords, beat

See discussion (65 comments, 220 points) - Archive

StreamVC: Real-Time Low-Latency Voice Conversion

See discussion (38 comments, 99 points) - Archive

AudioFlux: A C/C++ library for audio and music analysis

See discussion (54 comments, 230 points) - Archive

YouTube Video to Tabs and Lyrics

See discussion (48 comments, 135 points) - Archive