{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"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":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"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":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278},{"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":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"1803.09047","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","created":"2018-03-24","cited_by_count":173},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152},{"id":"2306.07691","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","created":"2023-06-13","cited_by_count":152},{"id":"1803.10963","title":"Attentive Statistics Pooling for Deep Speaker Embedding","created":"2018-03-29","cited_by_count":114},{"id":"1802.06006","title":"Neural Voice Cloning with a Few Samples","created":"2018-02-14","cited_by_count":100},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"1910.10838","title":"Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings","created":"2019-10-23","cited_by_count":73},{"id":"2110.04410","title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","created":"2021-10-08","cited_by_count":62},{"id":"2203.11389","title":"The VoiceMOS Challenge 2022","created":"2022-03-21","cited_by_count":57},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51},{"id":"1804.05160","title":"Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System","created":"2018-04-14","cited_by_count":47},{"id":"2204.00436","title":"AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios","created":"2022-04-01","cited_by_count":41},{"id":"2103.04088","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","created":"2021-03-06","cited_by_count":37},{"id":"2009.14153","title":"Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020","created":"2020-09-29","cited_by_count":36},{"id":"1907.02479","title":"Fine-grained robust prosody transfer for single-speaker neural text-to-speech","created":"2019-07-04","cited_by_count":27},{"id":"2002.01953","title":"BOFFIN TTS: Few-Shot Speaker Adaptation by Bayesian Optimization","created":"2020-02-04","cited_by_count":22},{"id":"2111.04040","title":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","created":"2021-11-07","cited_by_count":22},{"id":"2005.07973","title":"AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition","created":"2020-05-16","cited_by_count":19},{"id":"2104.09715","title":"AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data","created":"2021-04-20","cited_by_count":17},{"id":"2306.16083","title":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data","created":"2023-06-28","cited_by_count":15},{"id":"2010.12973","title":"Unsupervised Learning of Disentangled Speech Content and Style Representation","created":"2020-10-24","cited_by_count":13},{"id":"2202.10712","title":"nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-shot Multi-speaker Text-to-Speech","created":"2022-02-22","cited_by_count":10},{"id":"2203.15447","title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","created":"2022-03-29","cited_by_count":10},{"id":"2210.15868","title":"Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation","created":"2022-10-28","cited_by_count":10},{"id":"2203.15917","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","created":"2022-03-29","cited_by_count":8},{"id":"2010.06778","title":"Google Crowdsourced Speech Corpora and Related Open-Source Resources for Low-Resource Languages and Dialects: An Overview","created":"2020-10-14","cited_by_count":5},{"id":"2308.13007","title":"Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations","created":"2023-08-24","cited_by_count":5},{"id":"2207.04659","title":"Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data","created":"2022-07-11","cited_by_count":3},{"id":"2308.04177","title":"How Generalizable are Deepfake Image Detectors? An Empirical Study","created":"2023-08-08","cited_by_count":3}],"next_cursor":null}