{"total":52,"rows":[{"id":"2510.05096","title":"Paper2Video: Automatic Video Generation from Scientific Papers","created":"2025-10-06","cited_by_count":24,"area":null},{"id":"2510.06961","title":"Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation","created":"2025-10-08","cited_by_count":23,"area":null},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2505.21578","title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2505.22251","title":"Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2512.20308","title":"SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision","created":"2025-12-23","cited_by_count":8,"area":null},{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2509.12093","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2409.08655","title":"LMAC-TD: Producing Time Domain Explanations for Audio Classifiers","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2411.08013","title":"Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2412.13788","title":"Open Universal Arabic ASR Leaderboard","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2505.00579","title":"Voice Cloning: Comprehensive Survey","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2508.14623","title":"A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References","created":"2025-08-20","cited_by_count":4,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2411.14013","title":"Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints","created":"2024-11-21","cited_by_count":3,"area":null},{"id":"2506.01322","title":"Zero-Shot Text-to-Speech for Vietnamese","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2508.02038","title":"Marco-Voice Technical Report","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2510.10774","title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2511.10070","title":"ADI-20: Arabic Dialect Identification dataset and models","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2511.10780","title":"TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2511.13529","title":"Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2506.09521","title":"You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2509.26634","title":"Scaling Spoken Language Models with Syllabic Speech Tokenization","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2603.21900","title":"Ara-Best-RQ: Multi Dialectal Arabic SSL","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2501.06051","title":"Benchmarking Rotary Position Embeddings for Automatic Speech Recognition","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2502.18547","title":"Steganography Beyond Space-Time with Chain of Multimodal AI","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2507.12825","title":"Autoregressive Speech Enhancement via Acoustic Tokens","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2509.12101","title":"In-domain SSL pre-training and streaming ASR","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.09424","title":"The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.15383","title":"DroneAudioset: An Audio Dataset for Drone-based Search and Rescue","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2601.19946","title":"MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2603.21875","title":"Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2505.16911","title":"Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2506.10653","title":"Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2507.12701","title":"Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2507.23128","title":"Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shifts","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2510.07052","title":"Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2603.02030","title":"TCG CREST System Description for the DISPLACE-M Challenge","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.08282","title":"Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.08312","title":"Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.21940","title":"SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.02209","title":"CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.26281","title":"DiffAnon: Diffusion-based Prosody Control for Voice Anonymization","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.14766","title":"Streaming Speech-to-Text Translation with a SpeechLLM","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.17339","title":"SpeechDx: A Multi-Task Benchmark for Clinical Speech AI","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.22369","title":"Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.27627","title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.03414","title":"StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17278","title":"Nufo: A Benchmark for Ewe Automatic Speech Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}