{"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/portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","arxiv_id":"2109.15166","date":"2021-09-30","proceeding":"NeurIPS 2021 12","authors":["Yi Ren","Jinglin Liu","Zhou Zhao"],"abstract":"Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e.g., prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech model. Specifically, 1) to model both the prosody and mel-spectrogram details accurately, we adopt a lightweight VAE with an enhanced prior followed by a flow-based post-net with strong conditional inputs as the main architecture. 2) To further compress the model size and memory footprint, we introduce the grouped parameter sharing mechanism to the affine coupling layers in the post-net. 3) To improve the expressiveness of synthesized speech and reduce the dependency on accurate fine-grained alignment between text and speech, we propose a linguistic encoder with mixture alignment combining hard inter-word alignment and soft intra-word alignment, which explicitly extracts word-level semantic information. Experimental results show that PortaSpeech outperforms other TTS models in both voice quality and prosody modeling in terms of subjective and objective evaluation metrics, and shows only a slight performance degradation when reducing the model parameters to 6.7M (about 4x model size and 3x runtime memory compression ratio compared with FastSpeech 2). Our extensive ablation studies demonstrate that each design in PortaSpeech is effective.","url_abs":"https://arxiv.org/abs/2109.15166v5","url_pdf":"https://arxiv.org/pdf/2109.15166v5.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":"portaspeech-portable-and-high-quality","repo_url":"https://github.com/natspeech/natspeech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"portaspeech-portable-and-high-quality","repo_url":"https://github.com/MoonInTheRiver/DiffSinger","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"portaspeech-portable-and-high-quality","repo_url":"https://github.com/RayeRen/RayeRen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"portaspeech-portable-and-high-quality","repo_url":"https://github.com/keonlee9420/PortaSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"activation-normalization","method_name":"Activation Normalization"},{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fastspeech-2","method_name":"FastSpeech 2"},{"method_slug":"glow","method_name":"GLOW"},{"method_slug":"glow-tts","method_name":"Glow-TTS"},{"method_slug":"invertible-1x1-convolution","method_name":"Invertible 1x1 Convolution"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.15166","atlas_url":"https://app.syntology.ai/?focus=2109.15166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15166"}},"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/natspeech/natspeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MoonInTheRiver/DiffSinger","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/PortaSpeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RayeRen/RayeRen","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_honours":3,"ran_fixture":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":7,"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":1,"samples":[{"code_sha256_prefix":"a025408166aaff26","entry":"Embedding","repo":"natspeech/natspeech","repo_kind":"official","path":"modules/commons/layers.py","file_url":"https://github.com/natspeech/natspeech/blob/HEAD/modules/commons/layers.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":"a025408166aaff26"}},{"code_sha256_prefix":"59ae0708b1e8d94b","entry":"convert_pad_shape","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/blocks.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/blocks.py","link_basis":"harvester_set","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":"59ae0708b1e8d94b"}},{"code_sha256_prefix":"b38f9c28c5117398","entry":"fused_add_tanh_sigmoid_multiply","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/blocks.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b38f9c28c5117398"}},{"code_sha256_prefix":"03f2c896fd1d86dc","entry":"fused_add_tanh_sigmoid_multiply","repo":"natspeech/natspeech","repo_kind":"official","path":"modules/commons/wavenet.py","file_url":"https://github.com/natspeech/natspeech/blob/HEAD/modules/commons/wavenet.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":"03f2c896fd1d86dc"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"0f8f22937463d3c5","entry":"get_sinusoid_encoding_table","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/linguistic_encoder.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/linguistic_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f8f22937463d3c5"}},{"code_sha256_prefix":"ee17504855eec917","entry":"pad_input","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/postnet.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/postnet.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":"ee17504855eec917"}},{"code_sha256_prefix":"2b5c06c1ba593c3c","entry":"read_lexicon","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2b5c06c1ba593c3c"}},{"code_sha256_prefix":"88bf809d1bc9db4c","entry":"sequence_mask","repo":"natspeech/natspeech","repo_kind":"official","path":"modules/commons/rel_transformer.py","file_url":"https://github.com/natspeech/natspeech/blob/HEAD/modules/commons/rel_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88bf809d1bc9db4c"}},{"code_sha256_prefix":"2173110241f356ce","entry":"shift_1d","repo":"natspeech/natspeech","repo_kind":"official","path":"modules/commons/rel_transformer.py","file_url":"https://github.com/natspeech/natspeech/blob/HEAD/modules/commons/rel_transformer.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":"2173110241f356ce"}},{"code_sha256_prefix":"3feb059fe1daeee2","entry":"squeeze","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/postnet.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/postnet.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":"3feb059fe1daeee2"}},{"code_sha256_prefix":"c058572344c8f736","entry":"unsqueeze","repo":"keonlee9420/PortaSpeech","repo_kind":"listed","path":"model/postnet.py","file_url":"https://github.com/keonlee9420/PortaSpeech/blob/HEAD/model/postnet.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":"c058572344c8f736"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}