{"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/clarinet-parallel-wave-generation-in-end-to","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","arxiv_id":"1807.07281","date":"2018-07-19","proceeding":"ICLR 2019 5","authors":["Wei Ping","Kainan Peng","Jitong Chen"],"abstract":"In this work, we propose a new solution for parallel wave generation by\nWaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we\ndistill a Gaussian inverse autoregressive flow from the autoregressive WaveNet\nby minimizing a regularized KL divergence between their highly-peaked output\ndistributions. Our method computes the KL divergence in closed-form, which\nsimplifies the training algorithm and provides very efficient distillation. In\naddition, we introduce the first text-to-wave neural architecture for speech\nsynthesis, which is fully convolutional and enables fast end-to-end training\nfrom scratch. It significantly outperforms the previous pipeline that connects\na text-to-spectrogram model to a separately trained WaveNet (Ping et al.,\n2018). We also successfully distill a parallel waveform synthesizer conditioned\non the hidden representation in this end-to-end model.","url_abs":"http://arxiv.org/abs/1807.07281v3","url_pdf":"http://arxiv.org/pdf/1807.07281v3.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":"clarinet-parallel-wave-generation-in-end-to","repo_url":"https://github.com/dhgrs/chainer-ClariNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"clarinet-parallel-wave-generation-in-end-to","repo_url":"https://github.com/kensun0/Parallel-Wavenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"clarinet-parallel-wave-generation-in-end-to","repo_url":"https://github.com/ksw0306/ClariNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"clarinet-parallel-wave-generation-in-end-to","repo_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"clarinet-parallel-wave-generation-in-end-to","repo_url":"https://github.com/tiberiu44/TTS-Cube","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bridge-net","method_name":"Bridge-net"},{"method_slug":"clarinet","method_name":"ClariNet"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dv3-attention-block","method_name":"DV3 Attention Block"},{"method_slug":"dv3-convolution-block","method_name":"DV3 Convolution Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"softsign-activation","method_name":"Softsign Activation"},{"method_slug":"wavenet","method_name":"WaveNet"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"bridge-net","name":"Bridge-net","full_name":"Bridge-net"},{"slug":"clarinet","name":"ClariNet","full_name":"ClariNet"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.07281","atlas_url":"https://app.syntology.ai/?focus=1807.07281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.07281"}},"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/tiberiu44/TTS-Cube","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dhgrs/chainer-ClariNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kensun0/Parallel-Wavenet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ksw0306/ClariNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rickyHong/ClariNet-WaveNet-repl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_honours":1,"unverified":10},"by_repo_kind":{"listed":{"samples":13,"ran":3,"repositories":3}},"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":"4846dec26aaad0fb","entry":"collate_fn","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"data.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/data.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":"4846dec26aaad0fb"}},{"code_sha256_prefix":"ec4b02e7e489d13f","entry":"collate_fn_synthesize","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"data.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/data.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":"ec4b02e7e489d13f"}},{"code_sha256_prefix":"a42f23f7210ea856","entry":"log_sum_exp","repo":"tiberiu44/TTS-Cube","repo_kind":"listed","path":"cube/networks/loss.py","file_url":"https://github.com/tiberiu44/TTS-Cube/blob/HEAD/cube/networks/loss.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a42f23f7210ea856"}},{"code_sha256_prefix":"99b2eded38ce1abf","entry":"KL_gaussians","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/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":"99b2eded38ce1abf"}},{"code_sha256_prefix":"57c9f8e5bb12cb77","entry":"KL_gaussians","repo":"rickyHong/ClariNet-WaveNet-repl","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl/blob/HEAD/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":"57c9f8e5bb12cb77"}},{"code_sha256_prefix":"e2b09320a943125b","entry":"collate_fn","repo":"rickyHong/ClariNet-WaveNet-repl","repo_kind":"listed","path":"data.py","file_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl/blob/HEAD/data.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":"e2b09320a943125b"}},{"code_sha256_prefix":"a877c4698b24f4e6","entry":"gaussian_loss","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/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":"a877c4698b24f4e6"}},{"code_sha256_prefix":"09bc09927c87507a","entry":"gaussian_loss","repo":"rickyHong/ClariNet-WaveNet-repl","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl/blob/HEAD/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":"09bc09927c87507a"}},{"code_sha256_prefix":"0b918065d1f5caaf","entry":"load_checkpoint","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"synthesize_student.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/synthesize_student.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":"0b918065d1f5caaf"}},{"code_sha256_prefix":"500d31e7c971c941","entry":"load_checkpoint","repo":"rickyHong/ClariNet-WaveNet-repl","repo_kind":"listed","path":"synthesize_student.py","file_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl/blob/HEAD/synthesize_student.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":"500d31e7c971c941"}},{"code_sha256_prefix":"43151884ea330907","entry":"sample_from_gaussian","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/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":"43151884ea330907"}},{"code_sha256_prefix":"8c58c097caa4d2e6","entry":"sample_from_gaussian","repo":"rickyHong/ClariNet-WaveNet-repl","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/rickyHong/ClariNet-WaveNet-repl/blob/HEAD/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":"8c58c097caa4d2e6"}},{"code_sha256_prefix":"f3e80a7e162563ee","entry":"stft","repo":"ksw0306/ClariNet","repo_kind":"listed","path":"modules.py","file_url":"https://github.com/ksw0306/ClariNet/blob/HEAD/modules.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":"f3e80a7e162563ee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}