{"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/emilia-an-extensive-multilingual-and-diverse","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","arxiv_id":"2407.05361","date":"2024-07-07","proceeding":null,"authors":["Haorui He","Zengqiang Shang","Chaoren Wang","Xuyuan Li","Yicheng Gu","Hua Hua","Liwei Liu","Chen Yang","Jiaqi Li","Peiyang Shi","Yuancheng Wang","Kai Chen","Pengyuan Zhang","Zhizheng Wu"],"abstract":"Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present Emilia-Pipe, the first open-source preprocessing pipeline designed to efficiently transform raw, in-the-wild speech data into high-quality training data with speech annotations. Experimental results demonstrate the effectiveness of both Emilia and Emilia-Pipe. Demos are available at: https://emilia-dataset.github.io/Emilia-Demo-Page/.","url_abs":"https://arxiv.org/abs/2407.05361v3","url_pdf":"https://arxiv.org/pdf/2407.05361v3.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":"emilia-an-extensive-multilingual-and-diverse","repo_url":"https://github.com/open-mmlab/Amphion/blob/main/preprocessors/Emilia/README.md","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"}],"methods":[],"datasets_introduced":[{"slug":"emilia-dataset","name":"Emilia Dataset","full_name":"An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.05361","atlas_url":"https://app.syntology.ai/?focus=2407.05361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05361"}},"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/open-mmlab/Amphion/blob/main/preprocessors/Emilia/README.md","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":2},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":"e40f7b6dc5c3977a","entry":"get_human_readable_count","repo":"open-mmlab/Amphion","repo_kind":"official","path":"utils/model_summary.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/utils/model_summary.py","link_basis":"plan_row","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":"e40f7b6dc5c3977a"}},{"code_sha256_prefix":"eca6cdf05972a95e","entry":"l2norm","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/quantize/vector_quantize.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/quantize/vector_quantize.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eca6cdf05972a95e"}},{"code_sha256_prefix":"b5240484210b398a","entry":"laplace_smoothing","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/quantize/vector_quantize.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/quantize/vector_quantize.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5240484210b398a"}},{"code_sha256_prefix":"5923f41e711c0b69","entry":"safe_log","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/vocos.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/vocos.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":"5923f41e711c0b69"}},{"code_sha256_prefix":"ada1d74afbd92171","entry":"sample_vectors","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/quantize/vector_quantize.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/quantize/vector_quantize.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ada1d74afbd92171"}},{"code_sha256_prefix":"f247e4748f379a76","entry":"snake","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/codec.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/codec.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":"f247e4748f379a76"}},{"code_sha256_prefix":"db93710edf427df0","entry":"stft","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/loss.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/loss.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":"db93710edf427df0"}},{"code_sha256_prefix":"f1abe87534e9b4b5","entry":"symexp","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/vocos.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/vocos.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":"f1abe87534e9b4b5"}},{"code_sha256_prefix":"3acb919a94ac1a19","entry":"symlog","repo":"open-mmlab/Amphion","repo_kind":"official","path":"models/codec/amphion_codec/vocos.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/models/codec/amphion_codec/vocos.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":"3acb919a94ac1a19"}},{"code_sha256_prefix":"49d5adb77f62eba3","entry":"to_bytes","repo":"open-mmlab/Amphion","repo_kind":"official","path":"utils/model_summary.py","file_url":"https://github.com/open-mmlab/Amphion/blob/HEAD/utils/model_summary.py","link_basis":"first_harvest_node","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":"49d5adb77f62eba3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}