{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/advances-in-joint-ctc-attention-based-end-to","title":"Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM","arxiv_id":"1706.02737","date":"2017-06-08","proceeding":null,"authors":["Takaaki Hori","Shinji Watanabe","Yu Zhang","William Chan"],"abstract":"We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR)\nmodel. We learn to listen and write characters with a joint Connectionist\nTemporal Classification (CTC) and attention-based encoder-decoder network. The\nencoder is a deep Convolutional Neural Network (CNN) based on the VGG network.\nThe CTC network sits on top of the encoder and is jointly trained with the\nattention-based decoder. During the beam search process, we combine the CTC\npredictions, the attention-based decoder predictions and a separately trained\nLSTM language model. We achieve a 5-10\\% error reduction compared to prior\nsystems on spontaneous Japanese and Chinese speech, and our end-to-end model\nbeats out traditional hybrid ASR systems.","url_abs":"http://arxiv.org/abs/1706.02737v1","url_pdf":"http://arxiv.org/pdf/1706.02737v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/Alexander-H-Liu/End-to-end-ASR-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/mnm-rnd/elsa-voice-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/neil-zeng/asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/park-cheol/ASR-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/s3prl/End-to-end-ASR-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"advances-in-joint-ctc-attention-based-end-to","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02737","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}