D3L2 Speech Recognition with Deep Networks (by José A. R. Fonollosa)
Slides on: https://www.slideshare.net/xavigiro/speech-recognition-with-deep-neural-networks-d3l2-deep-learning-for-speech-and-language-upc-2017 ...
TALP_UPC Research Center
D3L6 End-to-end Speech Recognition with Recurrent Neural Networks (by José A. R. Fonollosa)
https://telecombcn-dl.github.io/2017-dlsl/ Deep Learning for Speech and Language Winter Seminar UPC TelecomBCN (January 24-31, 2017) The aim of this ...
TALP_UPC Research Center
Deep Learning на пальцах 11 - Аудио и распознавание речи (Юрий Бабуров)
Курс: http://dlcourse.ai Слайды: https://www.dropbox.com/s/tv3cv0ihq2l0u9f/Lecture%2011%20-%20Audio%20and%20Speech.pdf?dl=0.
sim0nsays
Lec14 Automatic Speech Recognition
The purpose of this course is to provide students with in-depth introduction on the articulation mechanism in human speech. Three main modules covered in the ...
NCTU OCW
Joint CTC-Attention based end to end speech recognition using multi-task learning
In this tutorial i explain the paper "Joint CTC-Attention based end to end speech recognition using multi-task learning" By Suyoun Kim, Takaaki Hori , and Shinji ...
Krishna D N
Connectionist Models of Cognition
In this video, I give an introduction to the field of computational cognitive modeling in general, and connectionist modeling in particular. We deal with: - The ...
Daniel Sabinasz
Word Recognition & Reading | Cognitive Psychology
This is a quick cognitive psychology video covering the different theories on word recognition and reading, and I briefly talk about dyslexia.
Christopher Tong 湯學榮
Alexey Pugachev -- Exploring Neural Transducers for End-to-End Speech Recognition
Overview of modern end-to-end speech recognition techniques. We will discuss why their properties are crucial for high-load and embedded systems. Slides: ...
St. Petersburg NLP Community
[ICASSP 2019] Fully Supervised Speaker Diarization: Say Goodbye to clustering
0:17 - Introduction 2:05 - Clustering - Why it's not good enough? 8:43 - UIS-RNN 17:06 - Experimental Results 20:17 - The Python Library 26:38 - Conclusions ...
Quan
How to build end-to-end recognition system (Part 1): best practices [RU]
In this lecture (Part 1) we will will consider the basic principles of building end-to-end recognition systems (speech recognition, image ocr). Slides: ...
Deep Systems
Connectionist Temporal Classification, Labelling Unsegmented Sequence Data with RNN | TDLS
Toronto Deep Learning Series, 9 July 2018 For slides and more information, visit https://tdls.a-i.science/events/2018-07-09/ Paper Review: ...
ML Explained - A.I. Socratic Circles - AISC
CTC for Offline Handwriting Recognition
Overview of CTC algorithm for handwriting recognition as part of a paper presentation for the Family History Technology Workshop at Brigham Young University ...
Oliver Nina
Speech Recognition using LSTM and CTC, Mohammad Gowayyed, Tiancheng Zhao, Florian Metze
Introduction to Machine Learning 10-701 CMU 2015 Projects: Speech Recognition using Deep LSTMs and CTC Mohammad Gowayyed, Tiancheng Zhao, ...
Alex Smola
(Old) Lecture 16 | Connectionist Temporal Classification
Carnegie Mellon University Course: 11-785, Intro to Deep Learning Offering: Spring 2019 Slides: http://deeplearning.cs.cmu.edu/slides.spring19/lec14.CTC.pdf ...
Carnegie Mellon University Deep Learning
M/12 Visual Speech recognition
Dive into Deep Learning UC Berkeley, STAT 157 Slides are at http://courses.d2l.ai The book is at http://www.d2l.ai.
Alex Smola
PRACTICAL TALK: DEEP LEARNING FOR SPEECH RECOGNITION (MARK GALES)
Bruno Martins
Models of word Recognition
Introduction to the Logogen model and the Interactive Activation Model A story made with Moovly, an easy and powerful online video animation tool. Try for free ...
Qiao Ying Chong
PSYCHOLINGUISTICS “Connectionist Models of Aphasia and Other Language Impairments”
Final project Psycholinguistics 6B.
rimpen cahyanti
SANE2018 | Takaaki Hori - End-to-end speech recognition in incomplete data scenarios
Takaaki Hori, Senior Principal Research Scientist at Mitsubishi Electric Research Labs (MERL), presents his work on how to leverage incomplete data for ...
Speech and Audio in the Northeast (SANE)
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
In this tutorial I will explain the paper " Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding" By Yuchen Liu, Jiajun ...
Krishna D N
[DLHLP 2020] Speech Recognition (2/7) - Listen, Attend, Spell
slides: http://speech.ee.ntu.edu.tw/~tlkagk/courses/DLHLP20/ASR%20(v12).pdf.
Hung-yi Lee
The State of Speech Recognition and the Future of Speech Understanding
Understanding and transcribing speech in a real-world, noisy environments is no simple task. In this session, we'll dissect speech recognition architectures of ...
Kranky Geek
Lecture 3.1.2 Automatic Speech Recognition
Automatic Speech Recognition.
NPTEL-NOC IITM
김지연 a comaprison of s2s models for speech recognition
딥러닝논문스터디 - 13번째 음성처리팀 김지연님의 'a comaprison of s2s models for speech recognition'입니다. 모임 참여 & 궁금 하신 사항은 댓글이나 ...
딥러닝논문읽기모임
The PyTorch-Kaldi Toolkit
A brief introduction to the PyTorch-Kaldi speech recognition toolkit.
Mirco Ravanelli
[DLHLP 2020] Speech Recognition (5/7) - Alignment of HMM, CTC and RNN-T (optional)
slides: http://speech.ee.ntu.edu.tw/~tlkagk/courses/DLHLP20/ASR2%20(v6).pdf 因為錄影時忘了關直播,導致背景有很明顯的人聲雜訊,還請見諒.
Hung-yi Lee
Very Deep Self-Attention Networks for End-to-End Speech Recognition
In this tutorial i will explain the paper "Very Deep Self-Attention Networks for End-to-End Speech Recognition" paper : https://arxiv.org/pdf/1904.13377.pdf.
Krishna D N
Deep Learning for Speech Recognition (Adam Coates, Baidu)
The talks at the Deep Learning School on September 24/25, 2016 were amazing. I clipped out individual talks from the full live streams and provided links to ...
Lex Fridman
Stanford Seminar - Deep Learning in Speech Recognition
EE380: Computer Systems Colloquium Seminar Deep Learning in Speech Recognition Speaker: Alex Acero, Apple Computer While neural networks had been ...
stanfordonline
Two-Pass End-to-End Speech Recognition
In this tutorial i will explain the paper "Two-Pass End-to-End Speech Recognition" By Tara N. Sainath, Ruoming Pang, David Rybach, Yanzhang He, Rohit ...
Krishna D N
C5W3L03 Beam Search
Deeplearning.ai
Demystifying speech recognition with Project DeepSpeech | PyConHK 2018
Our voices are no longer a mystery to speech recognition (SR) software, the technology powering these services has amazed the humanity with its ability to ...
PyCON Hong Kong
Towards end-to-end code switching speech recognition
In this tutorial i explain the paper "Towards end-to-end code switching speech recognition" by Ne Luo , Dongwei Jiang , Shuaijiang Zhao , Caixia Gong , Wei Zou ...
Krishna D N
ECCV 2016 - Connectionist Temporal Modeling for Weakly Supervised Action Labeling
Connectionist Temporal Modeling for Weakly Supervised Action Labeling De-An Huang, Li Fei-Fei, and Juan Carlos Niebles European Conference on ...
黃德安
DeepMind x UCL | Deep Learning Lectures | 8/12 | Attention and Memory in Deep Learning
Attention and memory have emerged as two vital new components of deep learning over the last few years. This lecture by DeepMind Research Scientist Alex ...
DeepMind
MyoSign: enabling end-to-end sign language recognition with wearables
MyoSign: enabling end-to-end sign language recognition with wearables Qian Zhang, Dong Wang, Run Zhao, Yinggang Yu IUI '19: 24th International ...
ACM SIGCHI
Lecture 7.4: Hynek Hermansky - Auditory Perception in Speech Technology, Part 1
MIT RES.9-003 Brains, Minds and Machines Summer Course, Summer 2015 View the complete course: https://ocw.mit.edu/RES-9-003SU15 Instructor: Hynek ...
MIT OpenCourseWare
Redesiging Neural Architectures for Sequence to Sequence Learning
The Encoder-Decoder model with soft-attention is now the defacto standard for sequence to sequence learning, having enjoyed early success in tasks like ...
Microsoft Research
Mixed Precision Training
This video explores Mixed Precision Training and new documentation for the Keras Mixed Precision Training API with Tensorflow 2.1 making this really easy to ...
Henry AI Labs
Future (Present?) of Machine Translation
It is quite easy to believe that the recently proposed approach to machine translation, called neural machine translation, is simply yet another approach to ...
Microsoft Research
What Kind of Computation is Human Cognition? A Brief History of Thought (Episode 1/2)
Since the naming of the field in 1956, AI has been dominated first by symbolic rule-based models, then early-generation neural (or “connectionist”) models, then ...
Microsoft Research
Yonatan Belinkov: Internal Representations in Deep Learning for Language and Speech Processing
Yonatan Belinkov Title: "Internal Representations in Deep Learning for Language and Speech Processing" Abstract: Language technology has become ...
Allen Institute for AI