{"url":"/method/espnet","slug":"espnet","name":"ESPNet","full_name":"ESPNet","full_name_withheld":false,"description_markdown":"**ESPNet** is a convolutional neural network for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a convolutional module, efficient spatial pyramid ([ESP](https://paperswithcode.com/method/esp)), which is efficient in terms of computation, memory, and power.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","first_author":"Sachin Mehta","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/espnet-efficient-spatial-pyramid-of-dilated"},"source":{"url":"http://arxiv.org/abs/1803.06815v3","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/sacmehta/ESPNet/blob/afe71c38edaee3514ca44e0adcafdf36109bf437/train/Model.py#L310","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Light-weight neural networks","url":"/methods/category/light-weight-neural-networks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":23,"archive_num_papers":23,"papers_newest_first":[{"paper":null,"title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning","date":"2025-05-31","arxiv_id":"2506.00338","n_code_links":0,"syntology":null},{"paper":"/paper/espnet-codec-comprehensive-training-and","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","date":"2024-09-24","arxiv_id":"2409.15897","n_code_links":2,"syntology":null},{"paper":null,"title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","date":"2024-09-14","arxiv_id":"2409.09506","n_code_links":0,"syntology":null},{"paper":null,"title":"The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization","date":"2024-07-23","arxiv_id":"2407.16447","n_code_links":0,"syntology":null},{"paper":null,"title":"A cost minimization approach to fix the vocabulary size in a tokenizer for an End-to-End ASR system","date":"2024-04-29","arxiv_id":"2406.02563","n_code_links":0,"syntology":null},{"paper":"/paper/euro-espnet-unsupervised-asr-open-source","title":"EURO: ESPnet Unsupervised ASR Open-source Toolkit","date":"2022-11-30","arxiv_id":"2211.17196","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/espnet-se-speech-enhancement-for-robust","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","date":"2022-07-19","arxiv_id":"2207.09514","n_code_links":1,"syntology":null},{"paper":null,"title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","date":"2022-06-27","arxiv_id":"2206.13135","n_code_links":0,"syntology":null},{"paper":null,"title":"NatiQ: An End-to-end Text-to-Speech System for Arabic","date":"2022-06-15","arxiv_id":"2206.07373","n_code_links":0,"syntology":null},{"paper":"/paper/eend-ss-joint-end-to-end-neural-speaker","title":"EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers","date":"2022-03-31","arxiv_id":"2203.17068","n_code_links":1,"syntology":null},{"paper":null,"title":"A Study of Transducer based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies","date":"2022-01-14","arxiv_id":"2201.05420","n_code_links":0,"syntology":null},{"paper":null,"title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","date":"2021-10-09","arxiv_id":"2110.04590","n_code_links":0,"syntology":null},{"paper":"/paper/daain-detection-of-anomalous-and-adversarial","title":"DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows","date":"2021-05-30","arxiv_id":"2105.14638","n_code_links":1,"syntology":null},{"paper":null,"title":"User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis","date":"2020-12-15","arxiv_id":"2101.03027","n_code_links":0,"syntology":null},{"paper":null,"title":"Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition","date":"2020-11-02","arxiv_id":"2011.00771","n_code_links":0,"syntology":null},{"paper":"/paper/a-crowdsourced-open-source-kazakh-speech","title":"A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline","date":"2020-09-22","arxiv_id":"2009.10334","n_code_links":1,"syntology":null},{"paper":"/paper/frame-to-frame-consistent-semantic","title":"Frame-To-Frame Consistent Semantic Segmentation","date":"2020-08-03","arxiv_id":"2008.00948","n_code_links":1,"syntology":null},{"paper":"/paper/espnet-tts-unified-reproducible-and","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","date":"2019-10-24","arxiv_id":"1910.10909","n_code_links":3,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":1}},{"paper":"/paper/self-supervised-sequence-to-sequence-asr","title":"Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text","date":"2019-04-30","arxiv_id":"1905.01152","n_code_links":0,"syntology":null},{"paper":"/paper/concentrated-comprehensive-convolutions-for","title":"C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation","date":"2018-12-12","arxiv_id":"1812.04920","n_code_links":2,"syntology":null},{"paper":"/paper/espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","date":"2018-11-28","arxiv_id":"1811.11431","n_code_links":10,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":0}},{"paper":null,"title":"ESPnet: End-to-End Speech Processing Toolkit","date":"2018-03-30","arxiv_id":"1804.00015","n_code_links":0,"syntology":null},{"paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","date":"2018-03-19","arxiv_id":"1803.06815","n_code_links":8,"syntology":{"ran":4,"of":10,"unverified":6,"pointer_only":0}}],"papers_shown":23,"tasks":[{"task":"/task/speech-recognition","name":"Speech Recognition","papers":12},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":11},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":9},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":8},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":5},{"task":"/task/segmentation","name":"Segmentation","papers":3},{"task":"/task/text-to-speech","name":"Text to Speech","papers":3},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":null,"name":"GPU","papers":2},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":2},{"task":"/task/speech-separation","name":"Speech Separation","papers":2},{"task":"/task/audio-generation","name":"Audio Generation","papers":1},{"task":"/task/distant-speech-recognition","name":"Distant Speech Recognition","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1}],"tasks_shown":20,"n_tasks":34,"usage_by_year":[{"year":"2018","papers":4},{"year":"2019","papers":2},{"year":"2020","papers":4},{"year":"2021","papers":2},{"year":"2022","papers":6},{"year":"2024","papers":4},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/espnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}