{"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/flowtron-an-autoregressive-flow-based","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","arxiv_id":"2005.05957","date":"2020-05-12","proceeding":"ICLR 2021 1","authors":["Rafael Valle","Kevin Shih","Ryan Prenger","Bryan Catanzaro"],"abstract":"In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opinion scores (MOS) show that Flowtron matches state-of-the-art TTS models in terms of speech quality. In addition, we provide results on control of speech variation, interpolation between samples and style transfer between speakers seen and unseen during training. Code and pre-trained models will be made publicly available at https://github.com/NVIDIA/flowtron","url_abs":"https://arxiv.org/abs/2005.05957v3","url_pdf":"https://arxiv.org/pdf/2005.05957v3.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":"flowtron-an-autoregressive-flow-based","repo_url":"https://github.com/NVIDIA/flowtron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"flowtron-an-autoregressive-flow-based","repo_url":"https://github.com/KathyReid/opensource-voice-tools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"flowtron-an-autoregressive-flow-based","repo_url":"https://github.com/NVIDIA/radtts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"location-sensitive-attention","method_name":"Location Sensitive Attention"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"tacotron-2","method_name":"Tacotron 2"},{"method_slug":"wavenet","method_name":"WaveNet"},{"method_slug":"zoneout","method_name":"Zoneout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"Flowtron","rank_in_archive_order":14,"of":16,"metrics":{"Pleasantness MOS":"3.665"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"Tacotron 2","rank_in_archive_order":15,"of":16,"metrics":{"Pleasantness MOS":"3.521"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.05957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05957"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/NVIDIA/radtts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KathyReid/opensource-voice-tools","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVIDIA/flowtron","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_violates":1,"unverified":15},"by_repo_kind":{"official":{"samples":17,"ran":2,"repositories":1},"listed":{"samples":2,"ran":2,"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":"83e2c862f7374ac7","entry":"dynamic_range_compression","repo":"NVIDIA/flowtron","repo_kind":"official","path":"audio_processing.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/audio_processing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83e2c862f7374ac7"}},{"code_sha256_prefix":"9f9ec26d4cdfdf7d","entry":"griffin_lim","repo":"NVIDIA/flowtron","repo_kind":"official","path":"audio_processing.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/audio_processing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"code_sha256_prefix":"8f4d7a02ebc32294","entry":"is_feature_invalid","repo":"NVIDIA/radtts","repo_kind":"listed","path":"inference_voice_conversion.py","file_url":"https://github.com/NVIDIA/radtts/blob/HEAD/inference_voice_conversion.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f4d7a02ebc32294"}},{"code_sha256_prefix":"1c566d43cb1220ba","entry":"lines_to_list","repo":"NVIDIA/radtts","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/NVIDIA/radtts/blob/HEAD/inference.py","link_basis":"first_harvest_node","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":"1c566d43cb1220ba"}},{"code_sha256_prefix":"360725578b4657a7","entry":"apply_gradient_allreduce","repo":"NVIDIA/flowtron","repo_kind":"official","path":"distributed.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/distributed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"360725578b4657a7"}},{"code_sha256_prefix":"1ae852ad9e56e415","entry":"beta_binomial_prior_distribution","repo":"NVIDIA/flowtron","repo_kind":"official","path":"data.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ae852ad9e56e415"}},{"code_sha256_prefix":"21a7f5b332d5b72b","entry":"expand_abbreviations","repo":"NVIDIA/flowtron","repo_kind":"official","path":"text/cleaners.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/text/cleaners.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21a7f5b332d5b72b"}},{"code_sha256_prefix":"4c6716f6a3894fe8","entry":"expand_numbers","repo":"NVIDIA/flowtron","repo_kind":"official","path":"text/cleaners.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/text/cleaners.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c6716f6a3894fe8"}},{"code_sha256_prefix":"c981f6e450532d4c","entry":"expand_safe_abbreviations","repo":"NVIDIA/flowtron","repo_kind":"official","path":"text/cleaners.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/text/cleaners.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c981f6e450532d4c"}},{"code_sha256_prefix":"3141eb646dea4007","entry":"get_gate_mask_from_lengths","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3141eb646dea4007"}},{"code_sha256_prefix":"18801918bcbf3ee3","entry":"get_mask_from_lengths","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"18801918bcbf3ee3"}},{"code_sha256_prefix":"3b8b2175be9ceb65","entry":"load_filepaths_and_text","repo":"NVIDIA/flowtron","repo_kind":"official","path":"data.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b8b2175be9ceb65"}},{"code_sha256_prefix":"df8c980fa0466884","entry":"load_wav_to_torch","repo":"NVIDIA/flowtron","repo_kind":"official","path":"data.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"df8c980fa0466884"}},{"code_sha256_prefix":"b01e085937691049","entry":"masked_instance_norm","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b01e085937691049"}},{"code_sha256_prefix":"9b7abc31835f4125","entry":"normalize_datestime","repo":"NVIDIA/flowtron","repo_kind":"official","path":"text/datestime.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/text/datestime.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b7abc31835f4125"}},{"code_sha256_prefix":"3d89a23ee4d0b639","entry":"plot_alignment_to_numpy","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron_plotting_utils.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron_plotting_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3d89a23ee4d0b639"}},{"code_sha256_prefix":"31de3dd8eeb3830a","entry":"plot_gate_outputs_to_numpy","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron_plotting_utils.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron_plotting_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31de3dd8eeb3830a"}},{"code_sha256_prefix":"a9bfcbb1d3623ba1","entry":"reduce_tensor","repo":"NVIDIA/flowtron","repo_kind":"official","path":"distributed.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/distributed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9bfcbb1d3623ba1"}},{"code_sha256_prefix":"29d749e3e95fa41d","entry":"save_figure_to_numpy","repo":"NVIDIA/flowtron","repo_kind":"official","path":"flowtron_plotting_utils.py","file_url":"https://github.com/NVIDIA/flowtron/blob/HEAD/flowtron_plotting_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29d749e3e95fa41d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}