{"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/non-parallel-sequence-to-sequence-voice","title":"Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations","arxiv_id":"1906.10508","date":"2019-06-25","proceeding":null,"authors":["Jing-Xuan Zhang","Zhen-Hua Ling","Li-Rong Dai"],"abstract":"This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of training data are introduced to provide the references for leaning linguistic representations of audio signals. Second, an adversarial training strategy is employed to further wipe out speaker information from the linguistic representations. Meanwhile, speaker representations are extracted from audio signals by a speaker encoder. The model parameters are estimated by two-stage training, including a pretraining stage using a multi-speaker dataset and a fine-tuning stage using the dataset of a specific conversion pair. Since both the recognition encoder and the decoder for recovering acoustic features are seq2seq neural networks, there are no constrains of frame alignment and frame-by-frame conversion in our proposed method. Experimental results showed that our method obtained higher similarity and naturalness than the best non-parallel voice conversion method in Voice Conversion Challenge 2018. Besides, the performance of our proposed method was closed to the state-of-the-art parallel seq2seq voice conversion method.","url_abs":"https://arxiv.org/abs/1906.10508v3","url_pdf":"https://arxiv.org/pdf/1906.10508v3.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"non-parallel-sequence-to-sequence-voice","repo_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.10508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10508"}},"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/jxzhanggg/nonparaSeq2seqVC_code","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"3205603a3de6d62a","entry":"apply_gradient_allreduce","repo":"jxzhanggg/nonparaSeq2seqVC_code","repo_kind":"official","path":"fine-tune/distributed.py","file_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/HEAD/fine-tune/distributed.py","link_basis":"first_harvest_node","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":"3205603a3de6d62a"}},{"code_sha256_prefix":"be7b0e3389efcecc","entry":"create_hparams","repo":"jxzhanggg/nonparaSeq2seqVC_code","repo_kind":"official","path":"fine-tune/hparams.py","file_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/HEAD/fine-tune/hparams.py","link_basis":"first_harvest_node","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":"be7b0e3389efcecc"}},{"code_sha256_prefix":"d88bad1cc5131afe","entry":"levenshteinDistance","repo":"jxzhanggg/nonparaSeq2seqVC_code","repo_kind":"official","path":"fine-tune/inference_utils.py","file_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/HEAD/fine-tune/inference_utils.py","link_basis":"first_harvest_node","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":"d88bad1cc5131afe"}},{"code_sha256_prefix":"5f66ebba9295bcce","entry":"sort_batch","repo":"jxzhanggg/nonparaSeq2seqVC_code","repo_kind":"official","path":"fine-tune/model/basic_layers.py","file_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/HEAD/fine-tune/model/basic_layers.py","link_basis":"first_harvest_node","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":"5f66ebba9295bcce"}},{"code_sha256_prefix":"69b8b31e44791260","entry":"tile","repo":"jxzhanggg/nonparaSeq2seqVC_code","repo_kind":"official","path":"fine-tune/model/basic_layers.py","file_url":"https://github.com/jxzhanggg/nonparaSeq2seqVC_code/blob/HEAD/fine-tune/model/basic_layers.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":"69b8b31e44791260"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}