{"url":"/method/dv3-attention-block","slug":"dv3-attention-block","name":"DV3 Attention Block","full_name":"DV3 Attention Block","full_name_withheld":false,"description_markdown":"**DV3 Attention Block** is an attention-based module used in the [Deep Voice 3](https://paperswithcode.com/method/deep-voice-3) architecture. It uses a [dot-product attention](https://paperswithcode.com/method/dot-product-attention) mechanism. A query vector (the hidden states of the decoder) and the per-timestep key vectors from the encoder are used to compute attention weights. This then outputs a context vector computed as the weighted average of the value vectors.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1710.07654v3","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/r9y9/deepvoice3_pytorch/blob/0b89c10cb473e032641c05cb8b105358c26c02b5/deepvoice3_pytorch/deepvoice3.py#L108","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Audio","area_id":"audio","collection":"Audio Model Blocks","url":"/methods/category/audio-model-blocks","pwc_aliases":[]}],"n_papers_tagged":9,"archive_num_papers":null,"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":"Parallel Neural Text-to-Speech","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"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}},{"paper":"/paper/deep-voice-3-scaling-text-to-speech-with","title":"Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning","date":"2017-10-20","arxiv_id":"1710.07654","n_code_links":7,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}}],"papers_shown":9,"tasks":[{"task":"/task/speech-synthesis","name":"Speech Synthesis","papers":4},{"task":"/task/text-to-speech","name":"Text to Speech","papers":4},{"task":"/task/text-to-speech-1","name":"text-to-speech","papers":4},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":2},{"task":"/task/unsupervised-domain-adaptation","name":"Unsupervised Domain Adaptation","papers":2},{"task":null,"name":"GPU","papers":1},{"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":9,"n_tasks":9,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":1},{"year":"2019","papers":3},{"year":"2020","papers":3},{"year":"2022","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dv3-attention-block"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}