{
  "id": 334401,
  "title": "[Resource] Related Papers 🎉",
  "url": "/competitions/dlsprint/discussion/334401",
  "author_name": "",
  "post_date": "2022-07-01T12:15:54.981089800Z",
  "votes": 16,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Adding links to few of the techniques and papers related to ASR task so you can have a look! <strong>Starter notebooks and EDAs are on their way too!</strong></p>\n<ul>\n<li><a href=\"https://www.mdpi.com/2073-8994/11/8/1018\" target=\"_blank\">An Overview of End-to-End Automatic Speech Recognition</a></li>\n<li><a href=\"https://arxiv.org/abs/2010.10504\" target=\"_blank\">Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition</a></li>\n<li><a href=\"https://arxiv.org/abs/2005.09629\" target=\"_blank\">Improved Noisy Student Training for Automatic Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/specaugment-a-simple-data-augmentation-method\" target=\"_blank\">SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/conformer-convolution-augmented-transformer\" target=\"_blank\">Conformer: Convolution-augmented Transformer for Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/advances-in-joint-ctc-attention-based-end-to\" target=\"_blank\">Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM</a></li>\n</ul>",
  "messages": [
    {
      "id": "1839436",
      "postDate": "07/01/2022 12:15:54",
      "content": "<p>Adding links to few of the techniques and papers related to ASR task so you can have a look! <strong>Starter notebooks and EDAs are on their way too!</strong></p>\n<ul>\n<li><a href=\"https://www.mdpi.com/2073-8994/11/8/1018\" target=\"_blank\">An Overview of End-to-End Automatic Speech Recognition</a></li>\n<li><a href=\"https://arxiv.org/abs/2010.10504\" target=\"_blank\">Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition</a></li>\n<li><a href=\"https://arxiv.org/abs/2005.09629\" target=\"_blank\">Improved Noisy Student Training for Automatic Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/specaugment-a-simple-data-augmentation-method\" target=\"_blank\">SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/conformer-convolution-augmented-transformer\" target=\"_blank\">Conformer: Convolution-augmented Transformer for Speech Recognition</a></li>\n<li><a href=\"https://paperswithcode.com/paper/advances-in-joint-ctc-attention-based-end-to\" target=\"_blank\">Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM</a></li>\n</ul>",
      "rawMarkdown": "Adding links to few of the techniques and papers related to ASR task so you can have a look! **Starter notebooks and EDAs are on their way too!**\n\n- [An Overview of End-to-End Automatic Speech Recognition](https://www.mdpi.com/2073-8994/11/8/1018)\n- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://arxiv.org/abs/2010.10504)\n- [Improved Noisy Student Training for Automatic Speech Recognition](https://arxiv.org/abs/2005.09629)\n- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://paperswithcode.com/paper/specaugment-a-simple-data-augmentation-method)\n- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://paperswithcode.com/paper/conformer-convolution-augmented-transformer)\n- [Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM](https://paperswithcode.com/paper/advances-in-joint-ctc-attention-based-end-to)",
      "votes": null
    },
    {
      "id": "1839449",
      "postDate": "07/01/2022 12:24:01",
      "content": "<p>Does the common voice dataset include bangali?</p>",
      "rawMarkdown": "Does the common voice dataset include bangali?",
      "votes": null
    },
    {
      "id": "1839452",
      "postDate": "07/01/2022 12:25:33",
      "content": "<p><a href=\"https://www.kaggle.com/hskhawaja\" target=\"_blank\">@hskhawaja</a> the dataset used for this competition only has Bengali data</p>",
      "rawMarkdown": "hskhawaja the dataset used for this competition only has Bengali data",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1839449,
      "author_name": "hskhawaja",
      "author_url": "",
      "post_date": "07/01/2022 12:24:01",
      "content": "<p>Does the common voice dataset include bangali?</p>",
      "votes": null,
      "replies": [
        {
          "id": 1839452,
          "author_name": "zarif98sjs",
          "author_url": "",
          "post_date": "07/01/2022 12:25:33",
          "content": "<p><a href=\"https://www.kaggle.com/hskhawaja\" target=\"_blank\">@hskhawaja</a> the dataset used for this competition only has Bengali data</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1839436": "Adding links to few of the techniques and papers related to ASR task so you can have a look! **Starter notebooks and EDAs are on their way too!**\n\n- [An Overview of End-to-End Automatic Speech Recognition](https://www.mdpi.com/2073-8994/11/8/1018)\n- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://arxiv.org/abs/2010.10504)\n- [Improved Noisy Student Training for Automatic Speech Recognition](https://arxiv.org/abs/2005.09629)\n- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://paperswithcode.com/paper/specaugment-a-simple-data-augmentation-method)\n- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://paperswithcode.com/paper/conformer-convolution-augmented-transformer)\n- [Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM](https://paperswithcode.com/paper/advances-in-joint-ctc-attention-based-end-to)",
    "1839449": "Does the common voice dataset include bangali?",
    "1839452": "hskhawaja the dataset used for this competition only has Bengali data"
  },
  "source": "meta"
}