{"total":192,"rows":[{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2401.16658","title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","created":"2024-01-30","cited_by_count":74,"area":null},{"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,"area":"lr"},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2402.12654","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","created":"2024-02-20","cited_by_count":37,"area":null},{"id":"2406.10507","title":"Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models","created":"2024-06-15","cited_by_count":29,"area":null},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2408.03468","title":"MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili","created":"2024-07-28","cited_by_count":25,"area":null},{"id":"2401.11943","title":"Benchmarking Large Multimodal Models against Common Corruptions","created":"2024-01-22","cited_by_count":24,"area":"lr"},{"id":"2505.13404","title":"Granary: Speech Recognition and Translation Dataset in 25 European Languages","created":"2025-05-19","cited_by_count":22,"area":null},{"id":"2407.06957","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","created":"2024-07-09","cited_by_count":21,"area":null},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20,"area":"ssm"},{"id":"2406.06097","title":"StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection","created":"2024-06-10","cited_by_count":19,"area":null},{"id":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19,"area":null},{"id":"2407.12229","title":"Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech","created":"2024-07-17","cited_by_count":19,"area":null},{"id":"2409.20201","title":"AfriHuBERT: A self-supervised speech representation model for African languages","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18,"area":null},{"id":"2412.18495","title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","created":"2024-12-24","cited_by_count":17,"area":null},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2401.05060","title":"MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector","created":"2024-01-10","cited_by_count":15,"area":null},{"id":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2407.21646","title":"Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent","created":"2024-07-31","cited_by_count":14,"area":"agents"},{"id":"2506.00087","title":"SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset","created":"2025-05-30","cited_by_count":14,"area":null},{"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,"area":null},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2409.02449","title":"What is lost in Normalization? Exploring Pitfalls in Multilingual ASR Model Evaluations","created":"2024-09-04","cited_by_count":13,"area":null},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2407.09818","title":"AraFinNLP 2024: The First Arabic Financial NLP Shared Task","created":"2024-07-13","cited_by_count":12,"area":null},{"id":"2407.15415","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2402.07383","title":"Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like","created":"2024-02-12","cited_by_count":11,"area":null},{"id":"2404.04904","title":"Cross-Domain Audio Deepfake Detection: Dataset and Analysis","created":"2024-04-07","cited_by_count":11,"area":null},{"id":"2407.01130","title":"Cross-Lingual Transfer Learning for Speech Translation","created":"2024-07-01","cited_by_count":11,"area":null},{"id":"2410.04324","title":"Where are we in audio deepfake detection? A systematic analysis over generative and detection models","created":"2024-10-06","cited_by_count":11,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2405.17809","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2406.09282","title":"On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2409.10985","title":"Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2405.20410","title":"SeamlessExpressiveLM: Speech Language Model for Expressive Speech-to-Speech Translation with Chain-of-Thought","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2507.05177","title":"OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2507.17527","title":"Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2603.08823","title":"Fish Audio S2 Technical Report","created":"2026-03-09","cited_by_count":9,"area":null},{"id":"2403.13169","title":"Wav2Gloss: Generating Interlinear Glossed Text from Speech","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2404.18534","title":"Evaluating and Mitigating Linguistic Discrimination in Large Language Models","created":"2024-04-29","cited_by_count":8,"area":"safety"},{"id":"2405.14161","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2503.05931","title":"Training and Inference Efficiency of Encoder-Decoder Speech Models","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2601.09385","title":"SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing","created":"2026-01-14","cited_by_count":8,"area":"mllm"},{"id":"2407.04533","title":"Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect","created":"2024-07-05","cited_by_count":7,"area":null},{"id":"2408.11849","title":"Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation","created":"2024-08-13","cited_by_count":7,"area":null},{"id":"2411.05945","title":"NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model","created":"2024-11-08","cited_by_count":7,"area":"moe"},{"id":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2509.02038","title":"NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task","created":"2025-09-02","cited_by_count":7,"area":null},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2602.11072","title":"Simultaneous Speech-to-Speech Translation Without Aligned Data","created":"2026-02-11","cited_by_count":7,"area":null},{"id":"2406.09494","title":"The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2408.07851","title":"SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition","created":"2024-08-14","cited_by_count":6,"area":null},{"id":"2409.16954","title":"Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2410.03458","title":"Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2507.07803","title":"StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model","created":"2025-07-10","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":"2406.00497","title":"Recent Advances in End-to-End Simultaneous Speech Translation","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2407.01777","title":"Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Models","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2410.16048","title":"Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion","created":"2024-10-21","cited_by_count":5,"area":"diffusion"},{"id":"2503.23542","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2504.11460","title":"Semantic Matters: Multimodal Features for Affective Analysis","created":"2025-03-16","cited_by_count":5,"area":null},{"id":"2505.15773","title":"ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.14177","title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2606.17742","title":"BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics","created":"2026-06-16","cited_by_count":5,"area":null},{"id":"2403.14168","title":"M$^3$AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2406.04512","title":"To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation","created":"2024-06-06","cited_by_count":4,"area":"distill"},{"id":"2409.13523","title":"EMMeTT: Efficient Multimodal Machine Translation Training","created":"2024-09-20","cited_by_count":4,"area":null},{"id":"2411.17170","title":"Overcoming Non-monotonicity in Transducer-based Streaming Generation","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2506.02742","title":"Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2509.24613","title":"HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2512.02593","title":"Spoken Conversational Agents with Large Language Models","created":"2025-12-02","cited_by_count":4,"area":"agents"},{"id":"2601.13319","title":"Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2402.05967","title":"The last Dance : Robust backdoor attack via diffusion models and bayesian approach","created":"2024-02-05","cited_by_count":3,"area":"diffusion"},{"id":"2406.10719","title":"Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach","created":"2024-06-15","cited_by_count":3,"area":null},{"id":"2406.18120","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2412.08274","title":"2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2503.22668","title":"Understanding Co-speech Gestures in-the-wild","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2506.11086","title":"Intelligibility of Text-to-Speech Systems for Mathematical Expressions","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2507.17578","title":"Synthetic Voice Data for Automatic Speech Recognition in African Languages","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2510.04213","title":"Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning","created":"2025-10-05","cited_by_count":3,"area":"distill"},{"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":"2403.14808","title":"A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterances","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2407.15828","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2408.13240","title":"Which Prosodic Features Matter Most for Pragmatics?","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2412.15415","title":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2412.15498","title":"The First Multilingual Model For The Detection of Suicide Texts","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2412.20359","title":"EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2503.17577","title":"Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2505.21230","title":"PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.24571","title":"Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.00748","title":"Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations","created":"2025-05-31","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}