{"list":"other","total":59,"rows":[{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"2005.11129","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","created":"2020-05-22","cited_by_count":273},{"id":"1909.08072","title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","created":"2019-09-17","cited_by_count":237},{"id":"1804.00308","title":"Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning","created":"2018-04-01","cited_by_count":225},{"id":"1910.03137","title":"Detecting AI Trojans Using Meta Neural Analysis","created":"2019-10-08","cited_by_count":199},{"id":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193},{"id":"1905.05879","title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","created":"2019-05-14","cited_by_count":192},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"1904.05441","title":"ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection","created":"2019-04-09","cited_by_count":178},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119},{"id":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"1904.05742","title":"One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization","created":"2019-04-10","cited_by_count":82},{"id":"2210.15418","title":"FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion","created":"2022-10-27","cited_by_count":80},{"id":"1806.02169","title":"StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks","created":"2018-06-06","cited_by_count":78},{"id":"2008.12527","title":"Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","created":"2020-08-28","cited_by_count":75},{"id":"1911.01840","title":"Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems","created":"2019-11-03","cited_by_count":67},{"id":"2010.11607","title":"Backdoor Attack against Speaker Verification","created":"2020-10-22","cited_by_count":66},{"id":"2010.13995","title":"One-class Learning Towards Synthetic Voice Spoofing Detection","created":"2020-10-27","cited_by_count":61},{"id":"2009.03728","title":"Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective","created":"2020-09-08","cited_by_count":59},{"id":"1705.02304","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System","created":"2017-05-05","cited_by_count":58},{"id":"2005.05957","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","created":"2020-05-12","cited_by_count":54},{"id":"2308.14970","title":"Audio Deepfake Detection: A Survey","created":"2023-08-29","cited_by_count":50},{"id":"2411.01156","title":"Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis","created":"2024-11-02","cited_by_count":48},{"id":"1801.03339","title":"Fooling End-to-end Speaker Verification by Adversarial Examples","created":"2018-01-10","cited_by_count":39},{"id":"2312.01479","title":"OpenVoice: Versatile Instant Voice Cloning","created":"2023-12-03","cited_by_count":32},{"id":"1910.08716","title":"Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification","created":"2019-10-19","cited_by_count":23},{"id":"1911.03078","title":"Adversarial Attacks on GMM i-vector based Speaker Verification Systems","created":"2019-11-08","cited_by_count":23},{"id":"2007.05979","title":"Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals","created":"2020-07-12","cited_by_count":22},{"id":"2109.00535","title":"ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan","created":"2021-09-01","cited_by_count":20},{"id":"2101.08909","title":"Study of Pre-processing Defenses against Adversarial Attacks on State-of-the-art Speaker Recognition Systems","created":"2021-01-22","cited_by_count":10},{"id":"2206.03351","title":"AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems","created":"2022-06-07","cited_by_count":10},{"id":"2306.07655","title":"Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systems","created":"2023-06-13","cited_by_count":10},{"id":"2306.15875","title":"Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion","created":"2023-06-28","cited_by_count":10},{"id":"2305.14097","title":"QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems","created":"2023-05-23","cited_by_count":9},{"id":"2205.13685","title":"Adversarial attacks and defenses in Speaker Recognition Systems: A survey","created":"2022-05-27","cited_by_count":6},{"id":"2211.08697","title":"PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking","created":"2022-11-16","cited_by_count":6},{"id":"2307.13643","title":"Backdoor Attacks against Voice Recognition Systems: A Survey","created":"2023-07-23","cited_by_count":6},{"id":"2408.09300","title":"Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model","created":"2024-08-17","cited_by_count":6},{"id":"2408.01178","title":"EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody","created":"2024-08-02","cited_by_count":5},{"id":"2203.13497","title":"WaveFuzz: A Clean-Label Poisoning Attack to Protect Your Voice","created":"2022-03-25","cited_by_count":4},{"id":"2410.12399","title":"SF-Speech: Straightened Flow for Zero-Shot Voice Clone","created":"2024-10-16","cited_by_count":4},{"id":"2201.01226","title":"Adversarial Transformation of Spoofing Attacks for Voice Biometrics","created":"2022-01-04","cited_by_count":3},{"id":"2506.01020","title":"DS-TTS: Zero-Shot Speaker Style Adaptation from Voice Clips via Dynamic Dual-Style Feature Modulation","created":"2025-06-01","cited_by_count":3},{"id":"2209.04547","title":"Defend Data Poisoning Attacks on Voice Authentication","created":"2022-09-09","cited_by_count":2},{"id":"2406.17277","title":"Securing Voice Authentication Applications Against Targeted Data Poisoning","created":"2024-06-25","cited_by_count":2},{"id":"2502.09553","title":"SyntheticPop: Attacking Speaker Verification Systems With Synthetic VoicePops","created":"2025-02-13","cited_by_count":2},{"id":"2505.03455","title":"Mitigating Backdoor Triggered and Targeted Data Poisoning Attacks in Voice Authentication Systems","created":"2025-05-06","cited_by_count":1}],"next_cursor":null}