{
  "id": 434887,
  "title": " Video Series: In Depth Explanation Of RNN-T based Automatic Speech Recognition Systems (ASR)",
  "url": "/competitions/bengaliai-speech/discussion/434887",
  "author_name": "Sinan Calisir",
  "post_date": "2023-08-27T02:19:40.375000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi everyone,</p>\n<p>I would like to share this video series on developing Automatic Speech Recognition Systems (ASR) using the RNN-T model.</p>\n<p><strong>The lecture series include:</strong></p>\n<ul>\n<li>Task of Automatic Speech Recognition (ASR) System<ul>\n<li>Input and Output</li>\n<li>Modularized (Hybrid) ASR</li>\n<li>Non Modularized (End2End) ASR</li></ul></li>\n<li>RNN-T Training</li>\n<li>RNN-T Decoding: Greedy Decoding</li>\n<li>RNN-T Beam Search Decoding</li>\n<li>Supplemental Content: Personalization of RNN-T ASR Systems</li>\n</ul>\n",
  "messages": [
    {
      "id": 2410484,
      "postDate": "2023-08-27T02:19:40.377Z",
      "content": "<p>Hi everyone,</p>\n<p>I would like to share this video series on developing Automatic Speech Recognition Systems (ASR) using the RNN-T model.</p>\n<p><strong>The lecture series include:</strong></p>\n<ul>\n<li>Task of Automatic Speech Recognition (ASR) System<ul>\n<li>Input and Output</li>\n<li>Modularized (Hybrid) ASR</li>\n<li>Non Modularized (End2End) ASR</li></ul></li>\n<li>RNN-T Training</li>\n<li>RNN-T Decoding: Greedy Decoding</li>\n<li>RNN-T Beam Search Decoding</li>\n<li>Supplemental Content: Personalization of RNN-T ASR Systems</li>\n</ul>\n",
      "rawMarkdown": "Hi everyone,\n\nI would like to share this video series on developing Automatic Speech Recognition Systems (ASR) using the RNN-T model.\n\n**The lecture series include:**\n\n- Task of Automatic Speech Recognition (ASR) System\n  - Input and Output\n  - Modularized (Hybrid) ASR\n  - Non Modularized (End2End) ASR\n- RNN-T Training\n- RNN-T Decoding: Greedy Decoding\n- RNN-T Beam Search Decoding\n- Supplemental Content: Personalization of RNN-T ASR Systems\n\n<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/videoseries?si=3xPpfnmOsUe9feWN&amp;list=PLapTxW9vHtzqMo6gS5zyn5YCNrz2xAm9W\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2410484": "Hi everyone,\n\nI would like to share this video series on developing Automatic Speech Recognition Systems (ASR) using the RNN-T model.\n\n**The lecture series include:**\n\n- Task of Automatic Speech Recognition (ASR) System\n  - Input and Output\n  - Modularized (Hybrid) ASR\n  - Non Modularized (End2End) ASR\n- RNN-T Training\n- RNN-T Decoding: Greedy Decoding\n- RNN-T Beam Search Decoding\n- Supplemental Content: Personalization of RNN-T ASR Systems\n\n<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/videoseries?si=3xPpfnmOsUe9feWN&amp;list=PLapTxW9vHtzqMo6gS5zyn5YCNrz2xAm9W\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>"
  }
}