{"total":47,"rows":[{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74,"area":null},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2306.01506","title":"BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models","created":"2023-06-02","cited_by_count":29,"area":null},{"id":"2205.15819","title":"Do self-supervised speech models develop human-like perception biases?","created":"2022-05-31","cited_by_count":28,"area":null},{"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,"area":null},{"id":"2302.12057","title":"ProsAudit, a prosodic benchmark for self-supervised speech models","created":"2023-02-23","cited_by_count":25,"area":null},{"id":"2203.05936","title":"Are discrete units necessary for Spoken Language Modeling?","created":"2022-03-11","cited_by_count":24,"area":null},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2305.04572","title":"Putting Natural in Natural Language Processing","created":"2023-05-08","cited_by_count":17,"area":null},{"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,"area":null},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","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":"2204.03310","title":"MTI-Net: A Multi-Target Speech Intelligibility Prediction Model","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2504.03036","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2305.19563","title":"Zero-Shot Automatic Pronunciation Assessment","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2505.23494","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2602.15537","title":"ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2603.29042","title":"An Empirical Recipe for Universal Phone Recognition","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2305.12501","title":"Exploring How Generative Adversarial Networks Learn Phonological Representations","created":"2023-05-21","cited_by_count":4,"area":null},{"id":"2210.12857","title":"Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2303.08809","title":"Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2308.00400","title":"ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2309.08773","title":"Enhance audio generation controllability through representation similarity regularization","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2504.03338","title":"BabyLM's First Words: Word Segmentation as a Phonological Probing Task","created":"2025-04-04","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":"2307.07325","title":"Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2312.11142","title":"Efficiency-oriented approaches for self-supervised speech representation learning","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2404.00856","title":"Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2407.02543","title":"Towards the Next Frontier in Speech Representation Learning Using Disentanglement","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2412.03074","title":"Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2506.15456","title":"Factorized RVQ-GAN For Disentangled Speech Tokenization","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2512.21204","title":"SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2603.05299","title":"WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.26978","title":"PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.16807","title":"Connecting Speech to Words through Images","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2402.01298","title":"Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2512.01865","title":"Cross-Lingual Interleaving for Speech Language Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.18612","title":"DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2608.26925","title":"Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.26992","title":"Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}