{"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/location-relative-attention-mechanisms-for","title":"Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis","arxiv_id":"1910.10288","date":"2019-10-23","proceeding":null,"authors":["Eric Battenberg","RJ Skerry-Ryan","Soroosh Mariooryad","Daisy Stanton","David Kao","Matt Shannon","Tom Bagby"],"abstract":"Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be addressed using simple location-relative attention mechanisms that do away with content-based query/key comparisons. We compare two families of attention mechanisms: location-relative GMM-based mechanisms and additive energy-based mechanisms. We suggest simple modifications to GMM-based attention that allow it to align quickly and consistently during training, and introduce a new location-relative attention mechanism to the additive energy-based family, called Dynamic Convolution Attention (DCA). We compare the various mechanisms in terms of alignment speed and consistency during training, naturalness, and ability to generalize to long utterances, and conclude that GMM attention and DCA can generalize to very long utterances, while preserving naturalness for shorter, in-domain utterances.","url_abs":"https://arxiv.org/abs/1910.10288v2","url_pdf":"https://arxiv.org/pdf/1910.10288v2.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":"location-relative-attention-mechanisms-for","repo_url":"https://github.com/anandaswarup/TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"location-relative-attention-mechanisms-for","repo_url":"https://github.com/anandaswarup/rnn-tts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"location-relative-attention-mechanisms-for","repo_url":"https://github.com/bshall/Tacotron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"location-relative-attention-mechanisms-for","repo_url":"https://github.com/coqui-ai/TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.10288","atlas_url":"https://app.syntology.ai/?focus=1910.10288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10288"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anandaswarup/rnn-tts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anandaswarup/TTS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coqui-ai/TTS","reach":{"status":"ok","spdx":"MPL-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bshall/Tacotron","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"669fcedc80c2fee3","entry":"load_checkpoint","repo":"anandaswarup/TTS","repo_kind":"listed","path":"train_Tacotron2.py","file_url":"https://github.com/anandaswarup/TTS/blob/HEAD/train_Tacotron2.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"669fcedc80c2fee3"}},{"code_sha256_prefix":"91be03213654f639","entry":"load_trained_model","repo":"anandaswarup/TTS","repo_kind":"listed","path":"tts_Synthesis.py","file_url":"https://github.com/anandaswarup/TTS/blob/HEAD/tts_Synthesis.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91be03213654f639"}},{"code_sha256_prefix":"3f1444600e75efac","entry":"zoneout","repo":"bshall/Tacotron","repo_kind":"listed","path":"tacotron/model.py","file_url":"https://github.com/bshall/Tacotron/blob/HEAD/tacotron/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f1444600e75efac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}