17: Kognitive Systeme, Vorlesung, SS 2018, 27.06.2018
Author
Editor
Participating institute
Institut für Anthropomatik und Robotik (IAR)
Genre
Description
- 0:00:00 Start
- 0:00:05 Speech Recognition
- 0:00:38 How good is a Recognizer
- 0:00:53 Dimensions of Difficulty
- 0:01:11 Speech Recognition (System Overview)
- 0:03:24 Die Fundamentalformel der Spracherkennung
- 0:05:07 Markov Models
- 0:06:06 Discrete Observation HMM
- 0:07:35 Hidden Markov Models
- 0:10:01 Acoustic Modeling
- 0:12:24 HMM Problems And Solutions
- 0:15:49 Evaluation
- 0:17:56 The Forward Algorithm
- 0:24:59 Forward Tellis
- 0:35:59 The Backward Algorithm
- 0:36:37 Backward Trellis
- 0:37:27 HMM Problems And Solutions
- 0:40:33 Decoding
- 0:46:35 Viterbi Trellis
- 0:54:55 Forward-Backward Algorithm
- 0:57:24 Training HMM Parameters
- 0:58:46 Baum-Welch Reestimation
- 1:01:05 HMMs In Speech recognition
- 1:03:49 Convergence of FB Algorithm
- 1:04:15 Model Topologies
- 1:05:28 Forward-Backward Training for Continuous Speech
- 1:05:46 Discrete HMMs Vector Quantization
- 1:09:37 Acoustic Modeling
- 1:12:14 Neural Net Approaches to Pattern Classification
- 1:14:00 Hidden Markov Models
- 1:15:14 HMMs in Speech Recognition
- 1:15:30 Dictionaries
- 1:16:54 Speech Recognition (System Components)
- 1:19:10 Language Models
- 1:23:27 Speech Recognition (Components)
Duration (hh:mm:ss)
01:24:27
Series
Kognitive Systeme, Vorlesung, SS 2018
Published on
05.07.2018
Subject area
License
| Resolution | 1280 x 720 Pixel |
| Aspect ratio | 16:9 |
| Audio bitrate | 128000 bps |
| Audio channels | 2 |
| Audio Codec | aac |
| Audio Sample Rate | 48000 Hz |
| Total Bitrate | 934060 bps |
| Color Space | yuv420p |
| Container | mov,mp4,m4a,3gp,3g2,mj2 |
| Media Type | video/mp4 |
| Duration | 5067 s |
| Filename | DIVA-2018-515_hd.mp4 |
| File Size | 591.573.695 byte |
| Frame Rate | 25 |
| Video Bitrate | 799959 bps |
| Video Codec | h264 |
Embed Code
Kognitive Systeme, Vorlesung, SS 2018
Episodes 1-21
of 21
