[SAIF 2020] Day 1: Towards End-to-End Speech Recognition - Tara Sainath | Samsung

11 544
10.1
Samsung7.01 млн
Опубликовано 12 ноября 2020, 0:02
End-to-end models allow us to represent the entire speech recognition pipeline (i.e., conventional acoustic, pronunciation and language models) by one neural network. This has huge implications for privacy, reliability and latency. In this talk, we will discuss the research developments around E2E models that have allowed it to reach the accuracy of conventional models, at a fraction of the model size and reduced latency. In addition, we will present further benefits of these models with respect to multi-lingual speech recognition.

#SAIF #SamsungAIForum

For more info, visit our page:
#SAIT(Samsung Advanced Institute of Technology): smsng.co/sait
Свежие видео
4 дня – 4 1600:26
Phone link on Xiaomi 14T Series
6 дней – 88 70735:06
Adam Savage Assembles His Raptor
9 дней – 25 20112:54
My last RTX 4000 Gaming PC.
9 дней – 6 6404:22
Google Axion Processors, explained
автотехномузыкадетское