Unsupervised Speech Recognition (Wav2Vec-U)

preview_player
Показать описание
In this tutorial, I explain the paper "Unsupervised Speech Recognition" By Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli

  1. MLOps Guru
Рекомендации по теме
Unsupervised Speech Recognition 0:56:00

Unsupervised Speech Recognition (Wav2Vec-U)

Wav2vec: Semi and 0:17:24

Wav2vec: Semi and Unsupervised Speech Recognition

Unsupervised Cross-lingual Representation 0:03:21

Unsupervised Cross-lingual Representation Learning for Speech Recognition - (3 minutes introduct...

Enhancing Unsupervised Speech 0:08:33

Enhancing Unsupervised Speech Recognition with Diffusion GANs - ICASSP2023

AAAI SAS 2022: 0:22:47

AAAI SAS 2022: Unsupervised speech segmentation (Invited Talk)

Wav2Vec: Unsupervised pre-training 0:24:41

Wav2Vec: Unsupervised pre-training for speech recognition

Simple and Effective 0:29:32

Simple and Effective Unsupervised Speech Synthesis

Almost Unsupervised Text 0:22:03

Almost Unsupervised Text to Speech and Automatic Speech Recognition

A quick weekly 0:03:49

A quick weekly summary of Facebook AI Blog on Unsupervised Speech Recognition and the Dynaboard

Exploring wav2vec 2.0 0:02:52

Exploring wav2vec 2.0 on speaker verification and language identification - (3 minutes introduct...

Toward Unsupervised Learning 0:47:08

Toward Unsupervised Learning of Speech Representations

60sec papers - 0:00:59

60sec papers - ​​wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Semi supervised Machine 0:27:52

Semi supervised Machine Learning for Speech Recognition - Lukas Neukom, Christian Scheller

wav2vec 2 0 0:01:06

wav2vec 2 0 A Framework for Self Supervised Learning of Speech Representations

wav2vec 2.0: A 0:45:11

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Interspeech 2021: Towards 0:03:05

Interspeech 2021: Towards unsupervised phone & word segmentation using vector-quantized NNs

Explore Wav2vec 2.0 0:03:14

Explore Wav2vec 2.0 for Mispronunciation Detection - (3 minutes introduction)

A comparison of 0:38:26

A comparison of self-supervised speech representations as input features for unsupervised AWEs

Wav2vec 2.0: Self-Supervised 1:04:05

Wav2vec 2.0: Self-Supervised Learning of Speech Representations #MLPaperReadingClubs

Cross-domain Speech Recognition 0:02:41

Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching - (3 min...

Joint Unsupervised and 0:18:35

Joint Unsupervised and Supervised Training for Multilingual ASR

Interspeech 2020: Achieving 0:13:33

Interspeech 2020: Achieving Multi Accent ASR via Unsupervised Acoustic Model Adaptation

Unsupervised Contrastive Learning 0:14:59

Unsupervised Contrastive Learning Of Sound Event Representations

Unsupervised Learning of 0:33:30

Unsupervised Learning of Spoken Language with Visual Context

Комментарии
Автор

Great work sir, please don't support this nice initiative.The world will remember you for your good work

pooravkadiyan
Автор

Thanks for this awesome explanation. Please share if any tutorial is available to train a data set from scratch.

SushantaKPani
Автор

Excellent video Krishna. A heads up, the paper URL link has expired.

aidansmyth
Автор

Nice explanation Krishna, I just want to know how we get the codebooks, do we learn them or are they pre-trained like transformers. In wav2vec, multiple codebooks are used, but it's not explained how they are acquired. Thanks again :)

MohammedBakheet
Автор

awesome stuff ! can i get the slides for this ?

imtiazkhan
Автор

I would be better if u use less fill out words like “ahh”

lbilly