{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"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":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126},{"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":"2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","created":"2020-11-23","cited_by_count":101},{"id":"2111.09344","title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage","created":"2021-11-17","cited_by_count":101},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101},{"id":"2305.18802","title":"LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus","created":"2023-05-30","cited_by_count":101},{"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":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81},{"id":"2411.17607","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","created":"2024-11-26","cited_by_count":47},{"id":"2506.10274","title":"Discrete Audio Tokens: More Than a Survey!","created":"2025-06-12","cited_by_count":38},{"id":"2108.00917","title":"Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing","created":"2021-08-02","cited_by_count":26},{"id":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24},{"id":"2501.15907","title":"Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation","created":"2025-01-27","cited_by_count":20},{"id":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19},{"id":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17},{"id":"2310.14580","title":"Acoustic BPE for Speech Generation with Discrete Tokens","created":"2023-10-23","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":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12},{"id":"2305.11435","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","created":"2023-05-19","cited_by_count":11},{"id":"2505.23494","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","created":"2025-05-29","cited_by_count":5},{"id":"2510.06195","title":"Latent Speech-Text Transformer","created":"2025-10-07","cited_by_count":5},{"id":"2602.15537","title":"ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling","created":"2026-02-17","cited_by_count":5},{"id":"2409.10103","title":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT","created":"2024-09-16","cited_by_count":4},{"id":"2505.17446","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","created":"2025-05-23","cited_by_count":4},{"id":"2503.06211","title":"LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models","created":"2025-03-08","cited_by_count":3},{"id":"2510.03639","title":"Towards Unsupervised Speech Recognition at the Syllable-Level","created":"2025-10-04","cited_by_count":2},{"id":"2601.22306","title":"Sylber 2.0: A Universal Syllable Embedding","created":"2026-01-29","cited_by_count":2}],"next_cursor":null}