{"url":"/method/clarinet","slug":"clarinet","name":"ClariNet","full_name":"ClariNet","full_name_withheld":false,"description_markdown":"**ClariNet** is an end-to-end text-to-speech architecture. Unlike previous TTS systems which use text-to-spectogram models with a separate waveform [synthesizer](https://paperswithcode.com/method/synthesizer) (vocoder), ClariNet is a text-to-wave architecture that is fully convolutional and can be trained from scratch. In ClariNet, the [WaveNet](https://paperswithcode.com/method/wavenet) module is conditioned on the hidden states instead of the mel-spectogram. The architecture is otherwise based on [Deep Voice 3](https://paperswithcode.com/method/deep-voice-3).","description_state":"present","introduced_year":null,"introduced_by":{"title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","paper":"/paper/clarinet-parallel-wave-generation-in-end-to","first_author":"Wei Ping","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/clarinet-parallel-wave-generation-in-end-to"},"source":{"url":"http://arxiv.org/abs/1807.07281v3","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Sequential","area_id":"sequential","collection":"Sequence To Sequence Models","url":"/methods/category/sequence-to-sequence-models","pwc_aliases":[]},{"area":"Audio","area_id":"audio","collection":"Text-to-Speech Models","url":"/methods/category/text-to-speech-models","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":"/paper/clarinet-a-music-retrieval-system","title":"Clarinet: A Music Retrieval System","date":"2022-10-23","arxiv_id":"2210.12648","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-a-complementary-label-source","title":"Learning from a Complementary-label Source Domain: Theory and Algorithms","date":"2020-08-04","arxiv_id":"2008.01454","n_code_links":1,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":4}},{"paper":"/paper/clarinet-a-one-step-approach-towards-budget","title":"Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation","date":"2020-07-29","arxiv_id":"2007.14612","n_code_links":1,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":4}},{"paper":null,"title":"Multi-Speaker End-to-End Speech Synthesis","date":"2019-07-09","arxiv_id":"1907.04462","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-neural-text-to-speech","title":"Non-Autoregressive Neural Text-to-Speech","date":"2019-05-21","arxiv_id":"1905.08459","n_code_links":2,"syntology":{"ran":2,"of":7,"unverified":5,"pointer_only":0}},{"paper":null,"title":"Neural source-filter waveform models for statistical parametric speech synthesis","date":"2019-04-27","arxiv_id":"1904.12088","n_code_links":0,"syntology":null},{"paper":"/paper/clarinet-parallel-wave-generation-in-end-to","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","date":"2018-07-19","arxiv_id":"1807.07281","n_code_links":5,"syntology":{"ran":1,"of":13,"unverified":12,"pointer_only":0}}],"papers_shown":7,"tasks":[{"task":"/task/speech-synthesis","name":"Speech Synthesis","papers":3},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":2},{"task":"/task/text-to-speech","name":"Text to Speech","papers":2},{"task":"/task/unsupervised-domain-adaptation","name":"Unsupervised Domain Adaptation","papers":2},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":2},{"task":"/task/melody-extraction","name":"Melody Extraction","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/text-to-speech-synthesis","name":"Text-To-Speech Synthesis","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":3},{"year":"2020","papers":2},{"year":"2022","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/clarinet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}