{"list":"other","total":85,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"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":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"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":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"1902.00275","title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","created":"2019-02-01","cited_by_count":262},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167},{"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":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2002.11800","title":"Universal Phone Recognition with a Multilingual Allophone System","created":"2020-02-26","cited_by_count":81},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78},{"id":"2006.03575","title":"End-to-End Adversarial Text-to-Speech","created":"2020-06-05","cited_by_count":77},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67},{"id":"2010.04301","title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","created":"2020-10-08","cited_by_count":65},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64},{"id":"2305.16608","title":"AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec","created":"2023-05-26","cited_by_count":47},{"id":"2309.07405","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","created":"2023-09-14","cited_by_count":44},{"id":"2002.09741","title":"VFlow: More Expressive Generative Flows with Variational Data Augmentation","created":"2020-02-22","cited_by_count":38},{"id":"2211.09407","title":"NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis","created":"2022-11-17","cited_by_count":38},{"id":"2305.10005","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","created":"2023-05-17","cited_by_count":37},{"id":"2404.02781","title":"CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech","created":"2024-04-03","cited_by_count":37},{"id":"2305.17651","title":"DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models","created":"2023-05-28","cited_by_count":36},{"id":"2203.16705","title":"Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion","created":"2022-03-30","cited_by_count":28},{"id":"1910.12590","title":"Detecting Multiple Speech Disfluencies using a Deep Residual Network with Bidirectional Long Short-Term Memory","created":"2019-10-17","cited_by_count":27},{"id":"2204.03417","title":"Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0","created":"2022-04-07","cited_by_count":27},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27},{"id":"2312.12810","title":"Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection","created":"2023-12-20","cited_by_count":21},{"id":"2310.02720","title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction","created":"2023-10-04","cited_by_count":17},{"id":"2310.10788","title":"Self-Supervised Models of Speech Infer Universal Articulatory Kinematics","created":"2023-10-16","cited_by_count":16},{"id":"2408.15297","title":"YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection","created":"2024-08-27","cited_by_count":16},{"id":"2401.10015","title":"Towards Hierarchical Spoken Language Dysfluency Modeling","created":"2024-01-18","cited_by_count":15},{"id":"2310.10803","title":"SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT","created":"2023-10-16","cited_by_count":13},{"id":"2204.00465","title":"Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition","created":"2022-04-01","cited_by_count":12},{"id":"2307.02471","title":"Deep Speech Synthesis from MRI-Based Articulatory Representations","created":"2023-07-05","cited_by_count":12},{"id":"2202.05396","title":"Enhancing ASR for Stuttered Speech with Limited Data Using Detect and Pass","created":"2022-02-08","cited_by_count":11},{"id":"2210.16498","title":"Articulatory Representation Learning Via Joint Factor Analysis and Neural Matrix Factorization","created":"2022-10-29","cited_by_count":11},{"id":"2205.05227","title":"Towards Improved Zero-shot Voice Conversion with Conditional DSVAE","created":"2022-05-11","cited_by_count":10},{"id":"2305.19255","title":"A Stutter Seldom Comes Alone -- Cross-Corpus Stuttering Detection as a Multi-label Problem","created":"2023-05-30","cited_by_count":9},{"id":"2206.02512","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","created":"2022-06-06","cited_by_count":7},{"id":"2306.00996","title":"Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling","created":"2023-05-30","cited_by_count":7},{"id":"2011.03689","title":"Detection and Evaluation of human and machine generated speech in spoofing attacks on automatic speaker verification systems","created":"2020-11-07","cited_by_count":6}],"next_cursor":null}