{"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/attentron-few-shot-text-to-speech-utilizing-1","title":"Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding","arxiv_id":"2005.08484","date":"2020-08-12","proceeding":null,"authors":[],"abstract":"On account of growing demands for personalization, the need for a so-called\nfew-shot TTS system that clones speakers with only a few data is emerging. To\naddress this issue, we propose Attentron, a few-shot TTS model that clones\nvoices of speakers unseen during training. It introduces two special encoders,\neach serving different purposes. A fine-grained encoder extracts\nvariable-length style information via an attention mechanism, and a\ncoarse-grained encoder greatly stabilizes the speech synthesis, circumventing\nunintelligible gibberish even for synthesizing speech of unseen speakers. In\naddition, the model can scale out to an arbitrary number of reference audios to\nimprove the quality of the synthesized speech. According to our experiments,\nincluding a human evaluation, the proposed model significantly outperforms\nstate-of-the-art models when generating speech for unseen speakers in terms of\nspeaker similarity and quality.","url_abs":"http://arxiv.org/abs/2005.08484v2","url_pdf":"http://arxiv.org/pdf/2005.08484v2.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":"attentron-few-shot-text-to-speech-utilizing-1","repo_url":"https://github.com/jasminsternkopf/mel_cepstral_distance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.08484","atlas_url":"https://app.syntology.ai/?focus=2005.08484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08484"}},"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/jasminsternkopf/mel_cepstral_distance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"listed":{"samples":8,"ran":7,"repositories":1}},"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":"e6f27aedfce3e43f","entry":"adjust_win_len_to_n_fft","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance/computation.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance/computation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6f27aedfce3e43f"}},{"code_sha256_prefix":"d79e21a23e4ff79f","entry":"amp_to_mag","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance/helper.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance/helper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d79e21a23e4ff79f"}},{"code_sha256_prefix":"6e4093cb3adc644b","entry":"mag_to_energy","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance/helper.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance/helper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e4093cb3adc644b"}},{"code_sha256_prefix":"d506928a11aa3b62","entry":"make_cache_key","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"experiments/run_experiments.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/experiments/run_experiments.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d506928a11aa3b62"}},{"code_sha256_prefix":"2f90604feeadcda6","entry":"plot_MC_X_ik","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance_analysis/helper.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance_analysis/helper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f90604feeadcda6"}},{"code_sha256_prefix":"2b5015c89644558b","entry":"remove_silence_rms","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance/silence.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance/silence.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b5015c89644558b"}},{"code_sha256_prefix":"23115e6c5bd95a8e","entry":"resample_if_necessary","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"src/mel_cepstral_distance/helper.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/src/mel_cepstral_distance/helper.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23115e6c5bd95a8e"}},{"code_sha256_prefix":"a1c9a92b090f0829","entry":"load_mos_dataset","repo":"jasminsternkopf/mel_cepstral_distance","repo_kind":"listed","path":"experiments/run_experiments.py","file_url":"https://github.com/jasminsternkopf/mel_cepstral_distance/blob/HEAD/experiments/run_experiments.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1c9a92b090f0829"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}