{"list":"other","total":57,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"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":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"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":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2010.15258","title":"DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors","created":"2020-10-28","cited_by_count":241},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2507.08128","title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","created":"2025-07-10","cited_by_count":219},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"2110.01763","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","created":"2021-10-05","cited_by_count":172},{"id":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","cited_by_count":83},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58},{"id":"2407.00463","title":"Open-Source Conversational AI with SpeechBrain 1.0","created":"2024-06-29","cited_by_count":56},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50},{"id":"2109.05418","title":"Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation","created":"2021-09-12","cited_by_count":48},{"id":"2406.06004","title":"FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model","created":"2024-06-10","cited_by_count":45},{"id":"2406.06992","title":"Scaling up masked audio encoder learning for general audio classification","created":"2024-06-11","cited_by_count":44},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33},{"id":"2501.11378","title":"Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio","created":"2025-01-20","cited_by_count":31},{"id":"2308.11957","title":"CED: Consistent ensemble distillation for audio tagging","created":"2023-08-23","cited_by_count":29},{"id":"2307.16425","title":"All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio","created":"2023-07-31","cited_by_count":28},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28},{"id":"1902.09254","title":"Audio Caption: Listen and Tell","created":"2019-02-25","cited_by_count":20},{"id":"2305.18283","title":"CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice","created":"2023-05-29","cited_by_count":20},{"id":"2407.04416","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","created":"2024-07-05","cited_by_count":15},{"id":"2306.16962","title":"Speech-based Age and Gender Prediction with Transformers","created":"2023-06-29","cited_by_count":14},{"id":"2406.13275","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","created":"2024-06-19","cited_by_count":14},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10},{"id":"2502.03979","title":"Towards Unified Music Emotion Recognition across Dimensional and Categorical Models","created":"2025-02-06","cited_by_count":7}],"next_cursor":null}