{"list":"other","total":64,"rows":[{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"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":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"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":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204},{"id":"2302.03540","title":"Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision","created":"2023-02-07","cited_by_count":169},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129},{"id":"2308.11596","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","created":"2023-08-22","cited_by_count":125},{"id":"2305.18802","title":"LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus","created":"2023-05-30","cited_by_count":101},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2309.08105","title":"Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context","created":"2023-09-15","cited_by_count":85},{"id":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2502.04128","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","created":"2025-02-06","cited_by_count":70},{"id":"2104.01497","title":"Hi-Fi Multi-Speaker English TTS Dataset","created":"2021-04-03","cited_by_count":60},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49},{"id":"2409.05377","title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","created":"2024-09-09","cited_by_count":46},{"id":"2502.07243","title":"Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement","created":"2025-02-11","cited_by_count":35},{"id":"2512.18099","title":"SAM Audio: Segment Anything in Audio","created":"2025-12-19","cited_by_count":30},{"id":"2402.13071","title":"Codec-SUPERB: An In-Depth Analysis of Sound Codec Models","created":"2024-02-20","cited_by_count":26},{"id":"2411.18803","title":"TS3-Codec: Transformer-Based Simple Streaming Single Codec","created":"2024-11-27","cited_by_count":25},{"id":"2506.23325","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","created":"2025-06-29","cited_by_count":23},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15},{"id":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15},{"id":"2010.11860","title":"Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models","created":"2020-10-22","cited_by_count":10},{"id":"2510.00981","title":"FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates","created":"2025-10-01","cited_by_count":10},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9},{"id":"2211.04610","title":"PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping","created":"2022-11-08","cited_by_count":8},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7},{"id":"2409.08711","title":"Text-To-Speech Synthesis In The Wild","created":"2024-09-13","cited_by_count":6},{"id":"2505.22487","title":"Effective Context in Neural Speech Models","created":"2025-05-28","cited_by_count":5},{"id":"2302.12391","title":"PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS","created":"2023-02-24","cited_by_count":4},{"id":"2508.20660","title":"CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation","created":"2025-08-28","cited_by_count":2},{"id":"2509.17143","title":"MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances","created":"2025-09-21","cited_by_count":1},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1}],"next_cursor":null}