HackerTube
HomeLongsLikedHistoryWatch laterCategoriesPlaylistsSettings

Speech Recognition Breakthrough for the Spoken, Translated Word

Microsoft Research1 HN recommender · recommended in 1 month, 2013-2024
YouTube
1M views · 14 years ago · demo · dated

Microsoft Research's Rick Rashid demonstrates a speech recognition and translation system, built on deep neural networks, that turns his spoken English into Chinese speech in 2012.

HN cites it as an early impressive real-time speech translation demo, often in discussions of voice-preserving translation and later AI demos.

Computer vision, speech & NLPMachine learning & deep learning#speechrecognition#machinetranslation#deepneuralnetworks#microsoftresearch#demo

4 comments from Hacker News

@Mystery-Machine2024 · in “GPT-4o”

Have you seen this video from Microsoft, uploaded to YT in 2012, the actual video could be even older: ▶ this video

CitesView on HN
@rlu2014 · in “Microsoft demos breakthrough in real-time translated conversations”

Reminds me of this from a few years ago: ▶ this video I feel like they should merge the two. The subtitles are a nice touch, but if it could capture the voice of the speaker it would be truly magical.

CitesView on HN
@istorical2014 · in “Say Hello to Cortana, Microsoft’s Siri Equivalent”

They've been doing some really cool stuff for a long time. Check out this real-time translation of spoken English into written and spoken Chinese (in the same voice of the speaker): ▶ this video

RecommendsView on HN
@taliesinb2013 · in “If Steve Ballmer Ran Apple”

Wasn't MSRA behind that amazing live English-to-Chinese translator [0]? It's interesting to contrast Google's and Microsoft's approach with ours at Wolfram Research (at 0.3% their size, of course [1]). We've come to see that it is very fruitful to live in a murky space somewhere between "commercial product" and "research project". I'm thinking specifically about Wolfram|Alpha. It's an enormous and daunting project. We've tackled a lot of very hard problems, and obviously have a long way still to go. It has the weird property of being a thing that ships every week, but not one that the parent company depends on financially. And so we kind of do our own thing, encoding domain knowledge, adding content, curating data, and designing frameworks, even if some if it won't ever make us any money (e.g. who will ever pay for dog vision [2]). We mostly just do things because they're cool or fun. But it's been incredibly useful to drive innovation elsewhere in the company. For example: 1. Alpha's unit system (the best in the world, the authors claim) is already in Mathematica 9. 2. Alpha is inspiring us to bring high-level semantic data and reasoning to Mathematica 10. 3. The automatic analysis in Pro is being souped up and will form part of Mathematica's predictive interface (automatic suggestions to "perform logistic regression", and so on). 4. We're working on taking the natural language understanding frameworks we've built for Alpha and using them to translate natural language querie

CitesView on HN
Lecture 1 | Natural Language Processing with Deep Learning1:11:41

Lecture 1 | Natural Language Processing with Deep Learning

Stanford University School of Engineering
820K views • 9 years ago
AI Language Models & Transformers - Computerphile20:39

AI Language Models & Transformers - Computerphile

Computerphile
354K views • 7 years ago
LSTM is dead. Long Live Transformers!28:48

LSTM is dead. Long Live Transformers!

Seattle Applied Deep Learning
540K views • 6 years ago
Larynx Demo54:13:03

Larynx Demo

synesthesiam
14K views • 5 years ago
The Eleventh HOPE (2016): Coding by Voice with Open Source Speech Recognition46:20

The Eleventh HOPE (2016): Coding by Voice with Open Source Speech Recognition

Channel2600
13K views • 9 years ago
CS231n Winter 2016: Lecture1: Introduction and Historical Context1:19:08

CS231n Winter 2016: Lecture1: Introduction and Historical Context

Andrej Karpathy
462K views • 10 years ago
Deep Visualization Toolbox3:54

Deep Visualization Toolbox

Jason Yosinski
270K views • 11 years ago
Duolingo -- the next chapter in human computation |  Luis von Ahn | TEDxCMU 201117:07

Duolingo -- the next chapter in human computation | Luis von Ahn | TEDxCMU 2011

TEDx Talks
394K views • 15 years ago
Introducing Word Lens1:10

Introducing Word Lens

QuestVisual
5.5M views • 15 years ago
Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition57:57

Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition

Stanford University School of Engineering
2.9M views • 9 years ago
Practical Deep Learning for Coders: Lesson 11:22:56

Practical Deep Learning for Coders: Lesson 1

Jeremy Howard
610K views • 4 years ago
Large Language Models from scratch8:25

Large Language Models from scratch

Graphics in 5 Minutes
375K views • 4 years ago
Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning48:10

Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning

Google TechTalks
123K views • 15 years ago
But how do AI images and videos actually work? | Guest video by Welch Labs37:20

But how do AI images and videos actually work? | Guest video by Welch Labs

3Blue1Brown
2.2M views • 1 year ago
Let's build the GPT Tokenizer2:13:35

Let's build the GPT Tokenizer

Andrej Karpathy
1.3M views • 2 years ago
Transformers, the tech behind LLMs | Deep Learning Chapter 527:14

Transformers, the tech behind LLMs | Deep Learning Chapter 5

3Blue1Brown
11.6M views • 2 years ago
This AI actually WORKS!!! - NVIDIA RTX Voice7:47

This AI actually WORKS!!! - NVIDIA RTX Voice

ShortCircuit
1.8M views • 6 years ago
The spelled-out intro to language modeling: building makemore1:57:45

The spelled-out intro to language modeling: building makemore

Andrej Karpathy
1.3M views • 4 years ago
Windows Vista Speech Recognition Tested - Perl Scripting10:34

Windows Vista Speech Recognition Tested - Perl Scripting

scrubadub1
913K views • 19 years ago
State of GPT | BRK216HFS42:40

State of GPT | BRK216HFS

Microsoft Developer
785K views • 3 years ago