{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/voice-cloning","name":"Voice Cloning","slug":"voice-cloning","description_markdown":"Voice cloning is a highly desired feature for personalized speech interfaces. Neural voice cloning system learns to synthesize a person’s voice from only a few audio samples.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":112,"papers_with_code":36,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/gneutralspeech-female","name":"GneutralSpeech Female","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gneutralspeech-male","name":"GneutralSpeech Male","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/audio-generation","name":"Audio Generation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":112,"of_with_code":36,"tagged_in_all":112,"counts":{"archive_papers_tagged":112,"with_a_code_link":36,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":112,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/transfer-learning-from-speaker-verification","slug":"transfer-learning-from-speaker-verification","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","date":"2018-06-12","arxiv_id":"1806.04558","repositories_listed":11,"syntology":null},{"url":"/paper/learning-to-speak-fluently-in-a-foreign","slug":"learning-to-speak-fluently-in-a-foreign","title":"Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning","date":"2019-07-09","arxiv_id":"1907.04448","repositories_listed":4,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-to-speak-fluently-in-a-foreign#ran","syntology_url":"https://syntology.ai/paper/1907.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.04448"}},"official":null}},{"url":"/paper/funaudiollm-voice-understanding-and","slug":"funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","arxiv_id":"2407.04051","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/funaudiollm-voice-understanding-and#ran","syntology_url":"https://syntology.ai/paper/2407.04051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04051"}},"official":{"repos":["FunAudioLLM/SenseVoice","funaudiollm/cosyvoice"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/enhancing-suno-s-bark-text-to-speech-model","slug":"enhancing-suno-s-bark-text-to-speech-model","title":"Enhancing Suno's Bark Text-to-Speech Model: Addressing Limitations Through Meta's Encodec and Pre-Trained Hubert","date":"2023-04-18","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/wavlm-model-ensemble-for-audio-deepfake","slug":"wavlm-model-ensemble-for-audio-deepfake","title":"WavLM model ensemble for audio deepfake detection","date":"2024-08-14","arxiv_id":"2408.07414","repositories_listed":2,"syntology":null},{"url":"/paper/anonymizing-speech-evaluating-and-designing","slug":"anonymizing-speech-evaluating-and-designing","title":"Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques","date":"2023-08-05","arxiv_id":"2308.04455","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-sat-speech-and-text-joint-pretraining-1","slug":"ernie-sat-speech-and-text-joint-pretraining-1","title":"ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech","date":"2022-11-07","arxiv_id":"2211.03545","repositories_listed":2,"syntology":null},{"url":"/paper/neural-voice-cloning-with-a-few-samples","slug":"neural-voice-cloning-with-a-few-samples","title":"Neural Voice Cloning with a Few Samples","date":"2018-02-14","arxiv_id":"1802.06006","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-voice-cloning-with-a-few-samples#ran","syntology_url":"https://syntology.ai/paper/1802.06006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06006"}},"official":null}},{"url":"/paper/few-shot-speech-deepfake-detection-adaptation","slug":"few-shot-speech-deepfake-detection-adaptation","title":"Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes","date":"2025-05-29","arxiv_id":"2505.23619","repositories_listed":1,"syntology":null},{"url":"/paper/cloneval-an-open-voice-cloning-benchmark","slug":"cloneval-an-open-voice-cloning-benchmark","title":"ClonEval: An Open Voice Cloning Benchmark","date":"2025-04-29","arxiv_id":"2504.20581","repositories_listed":1,"syntology":null},{"url":"/paper/speechdialoguefactory-generating-high-quality","slug":"speechdialoguefactory-generating-high-quality","title":"SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development","date":"2025-03-31","arxiv_id":"2503.23848","repositories_listed":1,"syntology":null},{"url":"/paper/2503-01710","slug":"2503-01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","date":"2025-03-03","arxiv_id":"2503.01710","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2503-01710#ran","syntology_url":"https://syntology.ai/paper/2503.01710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01710"}},"official":{"repos":["sparkaudio/spark-tts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/songgen-a-single-stage-auto-regressive","slug":"songgen-a-single-stage-auto-regressive","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","date":"2025-02-18","arxiv_id":"2502.13128","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/songgen-a-single-stage-auto-regressive#ran","syntology_url":"https://syntology.ai/paper/2502.13128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13128"}},"official":{"repos":["liuzh-19/songgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/step-audio-unified-understanding-and","slug":"step-audio-unified-understanding-and","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","date":"2025-02-17","arxiv_id":"2502.11946","repositories_listed":1,"syntology":null},{"url":"/paper/indextts-an-industrial-level-controllable-and","slug":"indextts-an-industrial-level-controllable-and","title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","date":"2025-02-08","arxiv_id":"2502.05512","repositories_listed":1,"syntology":null},{"url":"/paper/lina-speech-gated-linear-attention-is-a-fast","slug":"lina-speech-gated-linear-attention-is-a-fast","title":"Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis","date":"2024-10-30","arxiv_id":"2410.23320","repositories_listed":1,"syntology":null},{"url":"/paper/emoknob-enhance-voice-cloning-with-fine","slug":"emoknob-enhance-voice-cloning-with-fine","title":"EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control","date":"2024-10-01","arxiv_id":"2410.00316","repositories_listed":1,"syntology":null},{"url":"/paper/llamapartialspoof-an-llm-driven-fake-speech","slug":"llamapartialspoof-an-llm-driven-fake-speech","title":"LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation","date":"2024-09-23","arxiv_id":"2409.14743","repositories_listed":1,"syntology":null},{"url":"/paper/is-audio-spoof-detection-robust-to-laundering","slug":"is-audio-spoof-detection-robust-to-laundering","title":"Is Audio Spoof Detection Robust to Laundering Attacks?","date":"2024-08-27","arxiv_id":"2408.14712","repositories_listed":1,"syntology":null},{"url":"/paper/cosyvoice-a-scalable-multilingual-zero-shot","slug":"cosyvoice-a-scalable-multilingual-zero-shot","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","date":"2024-07-07","arxiv_id":"2407.05407","repositories_listed":1,"syntology":null},{"url":"/paper/xtts-a-massively-multilingual-zero-shot-text","slug":"xtts-a-massively-multilingual-zero-shot-text","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","date":"2024-06-07","arxiv_id":"2406.04904","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/xtts-a-massively-multilingual-zero-shot-text#ran","syntology_url":"https://syntology.ai/paper/2406.04904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04904"}},"official":{"repos":["Edresson/ZS-TTS-Evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/small-e-small-language-model-with-linear","slug":"small-e-small-language-model-with-linear","title":"Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis","date":"2024-06-06","arxiv_id":"2406.04467","repositories_listed":1,"syntology":null},{"url":"/paper/polyglotfake-a-novel-multilingual-and","slug":"polyglotfake-a-novel-multilingual-and","title":"PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset","date":"2024-05-14","arxiv_id":"2405.08838","repositories_listed":1,"syntology":null},{"url":"/paper/styledubber-towards-multi-scale-style","slug":"styledubber-towards-multi-scale-style","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","date":"2024-02-20","arxiv_id":"2402.12636","repositories_listed":1,"syntology":null},{"url":"/paper/proactive-detection-of-voice-cloning-with","slug":"proactive-detection-of-voice-cloning-with","title":"Proactive Detection of Voice Cloning with Localized Watermarking","date":"2024-01-30","arxiv_id":"2401.17264","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/proactive-detection-of-voice-cloning-with#ran","syntology_url":"https://syntology.ai/paper/2401.17264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17264"}},"official":{"repos":["facebookresearch/audioseal"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/openvoice-versatile-instant-voice-cloning","slug":"openvoice-versatile-instant-voice-cloning","title":"OpenVoice: Versatile Instant Voice Cloning","date":"2023-12-03","arxiv_id":"2312.01479","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/openvoice-versatile-instant-voice-cloning#ran","syntology_url":"https://syntology.ai/paper/2312.01479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01479"}},"official":null}},{"url":"/paper/single-and-multi-speaker-cloned-voice","slug":"single-and-multi-speaker-cloned-voice","title":"Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features","date":"2023-07-15","arxiv_id":"2307.07683","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/single-and-multi-speaker-cloned-voice#ran","syntology_url":"https://syntology.ai/paper/2307.07683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07683"}},"official":{"repos":["audio-df-ucb/clonedvoicedetection"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/low-resource-multilingual-and-zero-shot","slug":"low-resource-multilingual-and-zero-shot","title":"Low-Resource Multilingual and Zero-Shot Multispeaker TTS","date":"2022-10-21","arxiv_id":"2210.12223","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-study-incorporating-linguistic","slug":"empirical-study-incorporating-linguistic","title":"Empirical Study Incorporating Linguistic Knowledge on Filled Pauses for Personalized Spontaneous Speech Synthesis","date":"2022-10-14","arxiv_id":"2210.07559","repositories_listed":1,"syntology":null},{"url":"/paper/dictionary-attacks-on-speaker-verification","slug":"dictionary-attacks-on-speaker-verification","title":"Dictionary Attacks on Speaker Verification","date":"2022-04-24","arxiv_id":"2204.11304","repositories_listed":1,"syntology":null},{"url":"/paper/sig-vc-a-speaker-information-guided-zero-shot","slug":"sig-vc-a-speaker-information-guided-zero-shot","title":"SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines","date":"2021-11-06","arxiv_id":"2111.03811","repositories_listed":1,"syntology":null},{"url":"/paper/single-independent-component-recovery-and","slug":"single-independent-component-recovery-and","title":"Discovery of Single Independent Latent Variable","date":"2021-10-12","arxiv_id":"2110.05887","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/single-independent-component-recovery-and#ran","syntology_url":"https://syntology.ai/paper/2110.05887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05887"}},"official":{"repos":["shaham-lab/disilv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/txt2vid-ultra-low-bitrate-compression-of","slug":"txt2vid-ultra-low-bitrate-compression-of","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","date":"2021-06-26","arxiv_id":"2106.14014","repositories_listed":1,"syntology":null},{"url":"/paper/building-bilingual-and-code-switched-voice","slug":"building-bilingual-and-code-switched-voice","title":"Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency Loss","date":"2021-04-22","arxiv_id":"2104.10832","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-on-incorporating-pretrained-and","slug":"investigating-on-incorporating-pretrained-and","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","date":"2021-03-06","arxiv_id":"2103.04088","repositories_listed":1,"syntology":null},{"url":"/paper/one-model-many-languages-meta-learning-for","slug":"one-model-many-languages-meta-learning-for","title":"One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech","date":"2020-08-03","arxiv_id":"2008.00768","repositories_listed":1,"syntology":null},{"url":null,"slug":"pronunciation-deviation-analysis-through","title":"Pronunciation Deviation Analysis Through Voice Cloning and Acoustic Comparison","date":"2025-07-15","arxiv_id":"2507.10985","repositories_listed":0,"syntology":null},{"url":null,"slug":"de-antifake-rethinking-the-protective","title":"De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks","date":"2025-07-03","arxiv_id":"2507.02606","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-adaptation-for-swiss-german","title":"Voice Adaptation for Swiss German","date":"2025-05-28","arxiv_id":"2505.22054","repositories_listed":0,"syntology":null},{"url":null,"slug":"phir-hera-fairy-an-english-fairytaler-is-a","title":"Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages","date":"2025-05-27","arxiv_id":"2505.20693","repositories_listed":0,"syntology":null},{"url":null,"slug":"voicemark-zero-shot-voice-cloning-resistant","title":"VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents","date":"2025-05-27","arxiv_id":"2505.21568","repositories_listed":0,"syntology":null},{"url":null,"slug":"cloneshield-a-framework-for-universal","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","date":"2025-05-25","arxiv_id":"2505.19119","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-face-swapping-a-diffusion-based","title":"Beyond Face Swapping: A Diffusion-Based Digital Human Benchmark for Multimodal Deepfake Detection","date":"2025-05-22","arxiv_id":"2505.16512","repositories_listed":0,"syntology":null},{"url":null,"slug":"miku-pal-an-automated-and-standardized-multi","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","date":"2025-05-21","arxiv_id":"2505.15772","repositories_listed":0,"syntology":null},{"url":null,"slug":"voicecloak-a-multi-dimensional-defense","title":"VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning","date":"2025-05-18","arxiv_id":"2505.12332","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimax-speech-intrinsic-zero-shot-text-to","title":"MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder","date":"2025-05-12","arxiv_id":"2505.07916","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-cloning-comprehensive-survey","title":"Voice Cloning: Comprehensive Survey","date":"2025-05-01","arxiv_id":"2505.00579","repositories_listed":0,"syntology":null},{"url":null,"slug":"it-s-not-a-representation-of-me-examining","title":"\"It's not a representation of me\": Examining Accent Bias and Digital Exclusion in Synthetic AI Voice Services","date":"2025-04-12","arxiv_id":"2504.09346","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-global-voices-a-data-efficient","title":"Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis","date":"2025-04-10","arxiv_id":"2504.07858","repositories_listed":0,"syntology":null},{"url":null,"slug":"sok-how-robust-is-audio-watermarking-in","title":"SoK: How Robust is Audio Watermarking in Generative AI models?","date":"2025-03-24","arxiv_id":"2503.19176","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01266","title":"Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology","date":"2025-03-03","arxiv_id":"2503.01266","repositories_listed":0,"syntology":null},{"url":null,"slug":"steganography-beyond-space-time-with-chain-of","title":"Steganography Beyond Space-Time with Chain of Multimodal AI","date":"2025-02-25","arxiv_id":"2502.18547","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepfake-technology-unveiled-the","title":"Deepfake Technology Unveiled: The Commoditization of AI and Its Impact on Digital Trust","date":"2025-01-24","arxiv_id":"2506.07363","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-lightweight-and-stable-zero-shot-tts","title":"Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement","date":"2025-01-15","arxiv_id":"2501.08566","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars6-a-small-and-robust-hierarchical-codec","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","date":"2025-01-10","arxiv_id":"2501.05787","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-nam-to-speech-conversion-with-novel","title":"Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset","date":"2024-12-25","arxiv_id":"2412.18839","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-watermarking-with-discrete","title":"Speech Watermarking with Discrete Intermediate Representations","date":"2024-12-18","arxiv_id":"2412.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-stacked-aggregated-network-for-voice","title":"Parallel Stacked Aggregated Network for Voice Authentication in IoT-Enabled Smart Devices","date":"2024-11-29","arxiv_id":"2411.19841","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindi-audio-video-deepfake-hav-df-a-hindi","title":"Hindi audio-video-Deepfake (HAV-DF): A Hindi language-based Audio-video Deepfake Dataset","date":"2024-11-23","arxiv_id":"2411.15457","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-iscslp-2024-conversational-voice-clone","title":"The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings","date":"2024-10-31","arxiv_id":"2411.00064","repositories_listed":0,"syntology":null},{"url":null,"slug":"dmdspeech-distilled-diffusion-model","title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis","date":"2024-10-14","arxiv_id":"2410.11097","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-deepfake-speech-be-reliably-detected","title":"Can DeepFake Speech be Reliably Detected?","date":"2024-10-09","arxiv_id":"2410.06572","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-automatic-accentuation-and","title":"Algorithms For Automatic Accentuation And Transcription Of Russian Texts In Speech Recognition Systems","date":"2024-10-03","arxiv_id":"2410.02538","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmentation-through-laundering-attacks-for","title":"Augmentation through Laundering Attacks for Audio Spoof Detection","date":"2024-10-01","arxiv_id":"2410.01108","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-synthetic-training-data-for-speech","title":"Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space","date":"2024-09-19","arxiv_id":"2409.12745","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-adversarial-training-for-zero","title":"Multi-modal Adversarial Training for Zero-Shot Voice Cloning","date":"2024-08-28","arxiv_id":"2408.15916","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssl-tts-leveraging-self-supervised-embeddings","title":"kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech","date":"2024-08-20","arxiv_id":"2408.10771","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-voice-cloning-for-nepali-leveraging","title":"Advancing Voice Cloning for Nepali: Leveraging Transfer Learning in a Low-Resource Language","date":"2024-08-19","arxiv_id":"2408.10128","repositories_listed":0,"syntology":null},{"url":null,"slug":"preset-voice-matching-for-privacy-regulated","title":"Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems","date":"2024-07-18","arxiv_id":"2407.13153","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-speaker-multi-lingual-voice-cloning","title":"A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge","date":"2024-06-22","arxiv_id":"2406.17801","repositories_listed":0,"syntology":null},{"url":null,"slug":"dubwise-video-guided-speech-duration-control","title":"DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing","date":"2024-06-13","arxiv_id":"2406.08802","repositories_listed":0,"syntology":null},{"url":null,"slug":"just-because-we-camp-doesn-t-mean-we-should","title":"Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices","date":"2024-06-11","arxiv_id":"2406.07504","repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-language-corpora-augmentation-with","title":"Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech","date":"2024-06-11","arxiv_id":"2406.07090","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-autoregressive-real-time-accent","title":"Non-autoregressive real-time Accent Conversion model with voice cloning","date":"2024-05-21","arxiv_id":"2405.13162","repositories_listed":0,"syntology":null},{"url":"/paper/mobilespeech-a-fast-and-high-fidelity","slug":"mobilespeech-a-fast-and-high-fidelity","title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech","date":"2024-02-14","arxiv_id":"2402.09378","repositories_listed":0,"syntology":{"n":12,"n_ran":10,"n_constructed":6,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mobilespeech-a-fast-and-high-fidelity#ran","syntology_url":"https://syntology.ai/paper/2402.09378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09378"}},"official":null}},{"url":null,"slug":"scaling-nvidia-s-multi-speaker-multi-lingual","title":"Scaling NVIDIA's Multi-speaker Multi-lingual TTS Systems with Zero-Shot TTS to Indic Languages","date":"2024-01-24","arxiv_id":"2401.13851","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-accessibility-voice-cloning-and","title":"Empowering Communication: Speech Technology for Indian and Western Accents through AI-powered Speech Synthesis","date":"2024-01-22","arxiv_id":"2401.11771","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorycompanion-a-smart-healthcare-solution","title":"MemoryCompanion: A Smart Healthcare Solution to Empower Efficient Alzheimer's Care Via Unleashing Generative AI","date":"2023-11-20","arxiv_id":"2311.14730","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-self-2-0-how-ai-enhanced-self-clones","title":"Learning Through AI-Clones: Enhancing Self-Perception and Presentation Performance","date":"2023-10-23","arxiv_id":"2310.15112","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-speech-synthesis-with-minimal","title":"High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models","date":"2023-09-27","arxiv_id":"2309.15512","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-watermarking-for-adversarial","title":"Collaborative Watermarking for Adversarial Speech Synthesis","date":"2023-09-26","arxiv_id":"2309.15224","repositories_listed":0,"syntology":null},{"url":null,"slug":"travid-an-end-to-end-video-translation","title":"TRAVID: An End-to-End Video Translation Framework","date":"2023-09-20","arxiv_id":"2309.11338","repositories_listed":0,"syntology":null},{"url":"/paper/real-time-detection-of-ai-generated-speech","slug":"real-time-detection-of-ai-generated-speech","title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","date":"2023-08-24","arxiv_id":"2308.12734","repositories_listed":0,"syntology":null},{"url":null,"slug":"mega-tts-2-zero-shot-text-to-speech-with","title":"Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis","date":"2023-07-14","arxiv_id":"2307.07218","repositories_listed":0,"syntology":null},{"url":null,"slug":"taiwanese-accented-mandarin-and-english-multi","title":"Taiwanese-Accented Mandarin and English Multi-Speaker Talking-Face Synthesis System","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mix-and-match-an-empirical-study-on-training","title":"Mix and Match: An Empirical Study on Training Corpus Composition for Polyglot Text-To-Speech (TTS)","date":"2022-07-04","arxiv_id":"2207.01507","repositories_listed":0,"syntology":null},{"url":null,"slug":"utts-unsupervised-tts-with-conditional","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","date":"2022-06-06","arxiv_id":"2206.02512","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-robust-voice","title":"Self-supervised learning for robust voice cloning","date":"2022-04-07","arxiv_id":"2204.03421","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-few-shot-voice-cloning-using-multi","title":"Improve few-shot voice cloning using multi-modal learning","date":"2022-03-18","arxiv_id":"2203.09708","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-long-form-voice-cloning-with","title":"Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attention","date":"2022-01-25","arxiv_id":"2201.10375","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2c-visual-voice-cloning","title":"V2C: Visual Voice Cloning","date":"2021-11-25","arxiv_id":"2111.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-voice-fast-few-shot-style-transfer-for","title":"Meta-Voice: Fast few-shot style transfer for expressive voice cloning using meta learning","date":"2021-11-14","arxiv_id":"2111.07218","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-timbre-disentanglement-in-non","title":"Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech","date":"2021-10-14","arxiv_id":"2110.07192","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-cross-lingual-voice-cloning-using-low","title":"Improve Cross-lingual Voice Cloning Using Low-quality Code-switched Data","date":"2021-10-14","arxiv_id":"2110.07210","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-ipa-based-cross-lingual-text-to","title":"Revisiting IPA-based Cross-lingual Text-to-speech","date":"2021-10-14","arxiv_id":"2110.07187","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-tts-models-for-new-speakers-using","title":"Adapting TTS models For New Speakers using Transfer Learning","date":"2021-10-12","arxiv_id":"2110.05798","repositories_listed":0,"syntology":null},{"url":null,"slug":"translatotron-2-robust-direct-speech-to","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","date":"2021-07-19","arxiv_id":"2107.08661","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-presentation-creator-with-customized","title":"AI based Presentation Creator With Customized Audio Content Delivery","date":"2021-06-27","arxiv_id":"2106.14213","repositories_listed":0,"syntology":null},{"url":null,"slug":"preliminary-study-on-using-vector","title":"Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance","date":"2021-06-25","arxiv_id":"2106.13479","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-as-nu-system-for-the-m2voc-challenge","title":"The AS-NU System for the M2VoC Challenge","date":"2021-04-07","arxiv_id":"2104.03009","repositories_listed":0,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/voice-cloning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/voice-cloning/papers/2","json":"/task/voice-cloning/papers/2.json","rows":12},{"order":"ran","page":1,"of":1,"url":"/task/voice-cloning/papers/ran/1","json":"/task/voice-cloning/papers/ran/1.json","rows":11}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"dece74e370a35f65125a704ff662bf19f9961d38c4fd8d37a0dd62c130be0c0b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}