MIT 6.S191: Automatic Speech Recognition
Вставка
- Опубліковано 2 чер 2024
- MIT Introduction to Deep Learning 6.S191: Lecture 8
How Rev.com harnesses human-in-the-loop and deep learning to build the world's best English speech recognition engine
Lecturer: Miguel Jetté (Head of AI R&D) and Jennifer Drexler (Senior Speech Scientist)
Rev.AI
January 2022
For all lectures, slides, and lab materials: introtodeeplearning.com
Lecture Outline - coming soon!
Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!! - Наука та технологія
Thank you so much for all your efforts to make it open source! The lectures are really helpful 😄
Guest lectures this year are amazing!
You guys are so awesome for making these lectures public.
Thank you so much for the amazing lectures.
Can I recommend precision formats, because in the "REAL WORLD", transcription is one thing but also dialog level speech for mixed phonetics is critical along with hypothesis or word alternatives and confidence scores. A good test is a mixed alpha numeric. B's, T's, D's, E's, V's. I know you talk about transcription but if you want to go beyond that into conversational voice you need this in place. You also need to be careful on English. US English is US English, UK English is different again, as is international English. If you try to model English as US English you will fail. 30 years Speech rec experience here and designed delivered large scale speech and biometric systems. Happy to give you some commercial industrial insights for the real world. Ciao!
Thank you 👍
We Really appreciate your effort, bro. and congratulations on finishing your PHD
Thank You 💚
goog good
👍
how i can change live videos voice , like English voice to Hindi , how i can change your any video English voice to Hindi voice , i am not able to read caption
*Use chat gpt and other AI tools* 😊
Good
Are you working on speech recognition ? I am from Gujarat.
@@rajgothi970 yes
HELP