{"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/xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","arxiv_id":"2305.19709","date":"2023-05-31","proceeding":null,"authors":["Linh The Nguyen","Thinh Pham","Dat Quoc Nguyen"],"abstract":"We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. We publicly release our pre-trained XPhoneBERT with the hope that it would facilitate future research and downstream TTS applications for multiple languages. Our XPhoneBERT model is available at https://github.com/VinAIResearch/XPhoneBERT","url_abs":"https://arxiv.org/abs/2305.19709v1","url_pdf":"https://arxiv.org/pdf/2305.19709v1.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":"xphonebert-a-pre-trained-multilingual-model","repo_url":"https://github.com/vinairesearch/xphonebert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"xphonebert-a-pre-trained-multilingual-model","repo_url":"https://github.com/yl4579/StyleTTS2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.19709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19709"}},"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/yl4579/StyleTTS2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vinairesearch/xphonebert","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran":3,"unverified":13},"by_repo_kind":{"official":{"samples":18,"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":"59ae0708b1e8d94b","entry":"convert_pad_shape","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/commons.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/commons.py","link_basis":"plan_row","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":"a26f85d7c72ef39a","entry":"get_padding","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/commons.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/commons.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":"321604dda57bb02d","entry":"latest_checkpoint_path","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/utils.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/utils.py","link_basis":"plan_row","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":"321604dda57bb02d"}},{"code_sha256_prefix":"c647283e53cacacf","entry":"load_checkpoint","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/utils.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/utils.py","link_basis":"plan_row","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":"c647283e53cacacf"}},{"code_sha256_prefix":"70a7614b3b3eb41f","entry":"unconstrained_rational_quadratic_spline","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/transforms.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/transforms.py","link_basis":"plan_row","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":"70a7614b3b3eb41f"}},{"code_sha256_prefix":"896f7aae82a62114","entry":"discriminator_loss","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/losses.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/losses.py","link_basis":"plan_row","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":"896f7aae82a62114"}},{"code_sha256_prefix":"262807b9eb9706a5","entry":"dynamic_range_compression_torch","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/mel_processing.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/mel_processing.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":"262807b9eb9706a5"}},{"code_sha256_prefix":"78c12e563d5af53d","entry":"dynamic_range_decompression_torch","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/mel_processing.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/mel_processing.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":"78c12e563d5af53d"}},{"code_sha256_prefix":"cea1f83e9db28ed8","entry":"expand_abbreviations","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/text/cleaners.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/text/cleaners.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":"cea1f83e9db28ed8"}},{"code_sha256_prefix":"4c6716f6a3894fe8","entry":"expand_numbers","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/text/cleaners.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/text/cleaners.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":"4c6716f6a3894fe8"}},{"code_sha256_prefix":"24e8b4731dc3e070","entry":"feature_loss","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/losses.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/losses.py","link_basis":"plan_row","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":"24e8b4731dc3e070"}},{"code_sha256_prefix":"6191fd9efbdd55d4","entry":"generator_loss","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/losses.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/losses.py","link_basis":"plan_row","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":"6191fd9efbdd55d4"}},{"code_sha256_prefix":"c01a3efb274ff778","entry":"intersperse","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/commons.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/commons.py","link_basis":"plan_row","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":"c01a3efb274ff778"}},{"code_sha256_prefix":"296274b940cb0b32","entry":"lowercase","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/text/cleaners.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/text/cleaners.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":"296274b940cb0b32"}},{"code_sha256_prefix":"ba6cafc4d658c14f","entry":"piecewise_rational_quadratic_transform","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/transforms.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/transforms.py","link_basis":"plan_row","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":"ba6cafc4d658c14f"}},{"code_sha256_prefix":"d1de5b72a4f78810","entry":"plot_spectrogram_to_numpy","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/utils.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/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":"d1de5b72a4f78810"}},{"code_sha256_prefix":"e85d747983c4f5d8","entry":"searchsorted","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/transforms.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/transforms.py","link_basis":"plan_row","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":"e85d747983c4f5d8"}},{"code_sha256_prefix":"26b87488d429896a","entry":"spectral_normalize_torch","repo":"vinairesearch/xphonebert","repo_kind":"official","path":"VITS_with_XPhoneBERT/mel_processing.py","file_url":"https://github.com/vinairesearch/xphonebert/blob/HEAD/VITS_with_XPhoneBERT/mel_processing.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":"26b87488d429896a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}