{"list":"other","total":99,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"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":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"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":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"1810.12247","title":"Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset","created":"2018-10-29","cited_by_count":217},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"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":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169},{"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":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142},{"id":"2011.12998","title":"VoxLingua107: a Dataset for Spoken Language Recognition","created":"2020-11-25","cited_by_count":122},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118},{"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":"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":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100},{"id":"2006.07264","title":"Low-resource Languages: A Review of Past Work and Future Challenges","created":"2020-06-12","cited_by_count":91},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78},{"id":"1904.00784","title":"A Survey of Code-switched Speech and Language Processing","created":"2019-03-25","cited_by_count":75},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74},{"id":"2411.05361","title":"Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks","created":"2024-11-08","cited_by_count":71},{"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":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68},{"id":"2301.01967","title":"A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies","created":"2023-01-05","cited_by_count":59},{"id":"2410.12787","title":"The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio","created":"2024-10-16","cited_by_count":53},{"id":"1911.01799","title":"CN-CELEB: a challenging Chinese speaker recognition dataset","created":"2019-10-31","cited_by_count":48},{"id":"2503.01174","title":"Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics","created":"2025-03-03","cited_by_count":47},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45},{"id":"2408.01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","created":"2024-08-02","cited_by_count":44},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43},{"id":"2405.19103","title":"Voice Jailbreak Attacks Against GPT-4o","created":"2024-05-29","cited_by_count":42},{"id":"2505.13237","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","created":"2025-05-19","cited_by_count":42},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38},{"id":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33},{"id":"2411.07186","title":"NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics","created":"2024-11-11","cited_by_count":33},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31},{"id":"2410.16130","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","created":"2024-10-21","cited_by_count":31},{"id":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","cited_by_count":31},{"id":"2306.01506","title":"BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models","created":"2023-06-02","cited_by_count":29},{"id":"2412.05167","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","created":"2024-12-06","cited_by_count":29},{"id":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27},{"id":"2502.20616","title":"PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data","created":"2025-02-28","cited_by_count":27},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24},{"id":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23},{"id":"2212.02508","title":"MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning","created":"2022-12-05","cited_by_count":22},{"id":"2312.14069","title":"EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models","created":"2023-12-21","cited_by_count":22},{"id":"2407.18062","title":"Audio Entailment: Assessing Deductive Reasoning for Audio Understanding","created":"2024-07-25","cited_by_count":22},{"id":"2309.16953","title":"Enhancing Code-switching Speech Recognition with Interactive Language Biases","created":"2023-09-29","cited_by_count":21},{"id":"2406.02255","title":"MidiCaps: A large-scale MIDI dataset with text captions","created":"2024-06-04","cited_by_count":19},{"id":"2409.09927","title":"Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges","created":"2024-09-16","cited_by_count":18},{"id":"2409.04927","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","created":"2024-09-07","cited_by_count":16},{"id":"2502.09940","title":"A Preliminary Exploration with GPT-4o Voice Mode","created":"2025-02-14","cited_by_count":16},{"id":"2503.05085","title":"S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models","created":"2025-03-07","cited_by_count":16},{"id":"2504.00369","title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","created":"2025-04-01","cited_by_count":16},{"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":"2401.00273","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","created":"2023-12-30","cited_by_count":13},{"id":"2503.20290","title":"QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions","created":"2025-03-26","cited_by_count":13},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9},{"id":"2502.19759","title":"Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models","created":"2025-02-27","cited_by_count":9},{"id":"2408.16423","title":"WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language Understanding","created":"2024-08-29","cited_by_count":8},{"id":"2501.01034","title":"Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models","created":"2025-01-02","cited_by_count":8},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8},{"id":"2502.15919","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","created":"2025-02-21","cited_by_count":8},{"id":"2412.03075","title":"ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction","created":"2024-12-04","cited_by_count":7},{"id":"2408.13891","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","created":"2024-08-25","cited_by_count":6},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4},{"id":"2409.18941","title":"Building Trust Through Voice: How Vocal Tone Impacts User Perception of Attractiveness of Voice Assistants","created":"2024-09-27","cited_by_count":1}],"next_cursor":null}