{"id":13573547,"url":"https://github.com/nikhil-kotecha/Emotional_Dialogue","last_synced_at":"2025-04-04T12:31:11.142Z","repository":{"id":218426222,"uuid":"125909880","full_name":"nikhil-kotecha/Emotional_Dialogue","owner":"nikhil-kotecha","description":"A Deep Reinforcement Learning Approach (LSTM + policy gradient) to create a chatbot that produces coherent, emotional dialogue. ","archived":false,"fork":false,"pushed_at":"2018-05-07T11:22:24.000Z","size":164,"stargazers_count":26,"open_issues_count":2,"forks_count":10,"subscribers_count":0,"default_branch":"master","last_synced_at":"2024-11-05T08:37:03.129Z","etag":null,"topics":["cnn","lstm-neural-networks","policy-gradient","reinforcement-learning","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nikhil-kotecha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2018-03-19T19:30:42.000Z","updated_at":"2024-09-17T17:08:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"34ebb3de-f880-4efa-a1f2-eea28a397db2","html_url":"https://github.com/nikhil-kotecha/Emotional_Dialogue","commit_stats":null,"previous_names":["nikhil-kotecha/emotional_dialogue"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhil-kotecha%2FEmotional_Dialogue","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhil-kotecha%2FEmotional_Dialogue/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhil-kotecha%2FEmotional_Dialogue/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nikhil-kotecha%2FEmotional_Dialogue/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nikhil-kotecha","download_url":"https://codeload.github.com/nikhil-kotecha/Emotional_Dialogue/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247179604,"owners_count":20897073,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn","lstm-neural-networks","policy-gradient","reinforcement-learning","tensorflow"],"created_at":"2024-08-01T15:00:37.450Z","updated_at":"2025-04-04T12:31:06.202Z","avatar_url":"https://github.com/nikhil-kotecha.png","language":"Python","funding_links":[],"categories":["Chatbot"],"sub_categories":[],"readme":"# Emotional Speech and Chat \n\nThis project aims to implement and train all of the component models necessary for a chatbot which focuses on emotional relevance in chat. \n\nThe dialogue generation is completed using a reinforcement learning model. \n\nThe emotion recognition model classifies an input audio signal into one of six emotions: \n* happy\n* sad \n* frustrated \n* neutral \n* angry \n* excited \n\nThe speech recognition model is a reimplementation of Listen, Attend, and Spell by William Chen, et. al \n\nTraining functions are located in Jupyter notebooks for ease of running. \n\n#### Datasets used for training \n\n* IEMOCAP emotional dialogue: emotional speech recognition \n* Mozilla Common Voice: speech recognition \n* Cornell Movie Dialog Corpus: conversation generation\n\n#### Directories\n\n* rl_model: reinforcement learning models and training \n* speech_models: emotion and speech recognition models \n* utils: feature extraction and data loading helpers \n    \n#### Key References \n\n[1] Chan, William, et al. \"Listen, attend and spell.\" (2015). \n\n[2] Chernykh, Vladimir, Grigoriy Sterling, and Pavel Prihodko. \n\"Emotion recognition from speech with recurrent neural networks.\" \narXiv preprint arXiv:1701.08071 (2017).\n\n[3] Li, Jiwei, et al. \"Deep reinforcement learning for dialogue generation.\" \nrXiv preprint arXiv:1606.01541 (2016).\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikhil-kotecha%2FEmotional_Dialogue","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnikhil-kotecha%2FEmotional_Dialogue","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnikhil-kotecha%2FEmotional_Dialogue/lists"}