{"list":"other","total":51,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"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":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2106.06103","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","created":"2021-06-11","cited_by_count":561},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2010.15258","title":"DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors","created":"2020-10-28","cited_by_count":241},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2110.01200","title":"AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks","created":"2021-10-04","cited_by_count":180},{"id":"2011.01108","title":"End-to-end anti-spoofing with RawNet2","created":"2020-11-02","cited_by_count":164},{"id":"2109.00537","title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection","created":"2021-09-01","cited_by_count":161},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145},{"id":"2203.16263","title":"Does Audio Deepfake Detection Generalize?","created":"2022-03-30","cited_by_count":135},{"id":"2202.08433","title":"ADD 2022: the First Audio Deep Synthesis Detection Challenge","created":"2022-02-17","cited_by_count":96},{"id":"2408.08739","title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","created":"2024-08-16","cited_by_count":91},{"id":"2111.02813","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","created":"2021-11-04","cited_by_count":78},{"id":"2401.16658","title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","created":"2024-01-30","cited_by_count":74},{"id":"2111.04433","title":"RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing","created":"2021-11-08","cited_by_count":67},{"id":"2305.13774","title":"ADD 2023: the Second Audio Deepfake Detection Challenge","created":"2023-05-23","cited_by_count":64},{"id":"2401.09512","title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","created":"2024-01-17","cited_by_count":56},{"id":"2203.08488","title":"Pushing the limits of raw waveform speaker recognition","created":"2022-03-16","cited_by_count":51},{"id":"2204.05177","title":"The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance","created":"2022-04-11","cited_by_count":47},{"id":"1904.12088","title":"Neural source-filter waveform models for statistical parametric speech synthesis","created":"2019-04-27","cited_by_count":46},{"id":"2104.03617","title":"Half-Truth: A Partially Fake Audio Detection Dataset","created":"2021-04-08","cited_by_count":44},{"id":"2302.04215","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","created":"2023-02-08","cited_by_count":22},{"id":"2401.17230","title":"ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models","created":"2024-01-30","cited_by_count":22},{"id":"2210.10570","title":"Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders","created":"2022-10-19","cited_by_count":20},{"id":"2203.14732","title":"SASV 2022: The First Spoofing-Aware Speaker Verification Challenge","created":"2022-03-28","cited_by_count":19},{"id":"2207.12308","title":"CFAD: A Chinese Dataset for Fake Audio Detection","created":"2022-07-12","cited_by_count":14},{"id":"2204.01005","title":"Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification","created":"2022-04-03","cited_by_count":10},{"id":"2305.19051","title":"Towards single integrated spoofing-aware speaker verification embeddings","created":"2023-05-30","cited_by_count":7},{"id":"2006.05599","title":"Integrated Replay Spoofing-aware Text-independent Speaker Verification","created":"2020-06-10","cited_by_count":6},{"id":"2110.09441","title":"FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection","created":"2021-10-18","cited_by_count":6},{"id":"2403.01355","title":"a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification","created":"2024-03-03","cited_by_count":6},{"id":"2409.08711","title":"Text-To-Speech Synthesis In The Wild","created":"2024-09-13","cited_by_count":6},{"id":"1602.02950","title":"Spoofing detection under noisy conditions: a preliminary investigation and an initial database","created":"2016-02-09","cited_by_count":2},{"id":"2406.05339","title":"To what extent can ASV systems naturally defend against spoofing attacks?","created":"2024-06-08","cited_by_count":1}],"next_cursor":null}