{"list":"other","total":69,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","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":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","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":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"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":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"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":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210},{"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":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"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":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"2206.08317","title":"Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition","created":"2022-06-16","cited_by_count":144},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141},{"id":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2105.14762","title":"Emotional Voice Conversion: Theory, Databases and ESD","created":"2021-05-31","cited_by_count":115},{"id":"2010.11567","title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","created":"2020-10-22","cited_by_count":111},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"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":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83},{"id":"2501.06282","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","created":"2025-01-10","cited_by_count":79},{"id":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70},{"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":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68},{"id":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62},{"id":"2410.17799","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","created":"2024-10-23","cited_by_count":60},{"id":"2411.09943","title":"Zero-shot Voice Conversion with Diffusion Transformers","created":"2024-11-15","cited_by_count":43},{"id":"2203.16844","title":"Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset","created":"2022-03-31","cited_by_count":40},{"id":"2406.05763","title":"WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark","created":"2024-06-09","cited_by_count":40},{"id":"2211.02289","title":"CochlScene: Acquisition of acoustic scene data using crowdsourcing","created":"2022-11-04","cited_by_count":33},{"id":"2104.04214","title":"What is the ground truth? Reliability of multi-annotator data for audio tagging","created":"2021-04-09","cited_by_count":29},{"id":"1804.05788","title":"Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning","created":"2018-04-16","cited_by_count":21},{"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":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18},{"id":"2212.00406","title":"High Fidelity Speech Enhancement with Band-split RNN","created":"2022-12-01","cited_by_count":16},{"id":"2309.13905","title":"AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data","created":"2023-09-25","cited_by_count":16},{"id":"2501.13306","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","created":"2025-01-23","cited_by_count":13},{"id":"2404.12195","title":"OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data","created":"2024-04-18","cited_by_count":3},{"id":"2402.07485","title":"MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning","created":"2024-02-12","cited_by_count":1}],"next_cursor":null}