{"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/diffgan-tts-high-fidelity-and-efficient-text","title":"DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs","arxiv_id":"2201.11972","date":"2022-01-28","proceeding":null,"authors":["Songxiang Liu","Dan Su","Dong Yu"],"abstract":"Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to use in real-time speech processing applications. In this paper, we introduce DiffGAN-TTS, a novel DDPM-based text-to-speech (TTS) model achieving high-fidelity and efficient speech synthesis. DiffGAN-TTS is based on denoising diffusion generative adversarial networks (GANs), which adopt an adversarially-trained expressive model to approximate the denoising distribution. We show with multi-speaker TTS experiments that DiffGAN-TTS can generate high-fidelity speech samples within only 4 denoising steps. We present an active shallow diffusion mechanism to further speed up inference. A two-stage training scheme is proposed, with a basic TTS acoustic model trained at stage one providing valuable prior information for a DDPM trained at stage two. Our experiments show that DiffGAN-TTS can achieve high synthesis performance with only 1 denoising step.","url_abs":"https://arxiv.org/abs/2201.11972v1","url_pdf":"https://arxiv.org/pdf/2201.11972v1.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":"diffgan-tts-high-fidelity-and-efficient-text","repo_url":"https://github.com/keonlee9420/DiffGAN-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diffgan-tts-high-fidelity-and-efficient-text","repo_url":"https://github.com/komyeongjin/specdiff-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"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":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.11972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11972"}},"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/komyeongjin/specdiff-gan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/DiffGAN-TTS","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"ran_violates":2,"ran_honours":1,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"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":"a3e27bd1e8b628ed","entry":"Embedding","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/blocks.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3e27bd1e8b628ed"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/blocks.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/blocks.py","link_basis":"harvester_set","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":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"fbf9ec7be545688e","entry":"default","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/diffusion.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbf9ec7be545688e"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/diffusion.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"hifigan/models.py","file_url":"https://github.com/komyeongjin/specdiff-gan/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":"09c8479d9a5b3e06","entry":"extract","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/diffusion.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/diffusion.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":"09c8479d9a5b3e06"}},{"code_sha256_prefix":"61fbf11e413124d1","entry":"get_adversarial_losses_fn","repo":"komyeongjin/specdiff-gan","repo_kind":"listed","path":"model/loss.py","file_url":"https://github.com/komyeongjin/specdiff-gan/blob/HEAD/model/loss.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":"61fbf11e413124d1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}