{"total":43,"rows":[{"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"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":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19,"area":null},{"id":"2305.11411","title":"DUB: Discrete Unit Back-translation for Speech Translation","created":"2023-05-19","cited_by_count":18,"area":null},{"id":"2310.10788","title":"Self-Supervised Models of Speech Infer Universal Articulatory Kinematics","created":"2023-10-16","cited_by_count":16,"area":null},{"id":"2306.02405","title":"An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech","created":"2023-06-04","cited_by_count":15,"area":null},{"id":"2502.07029","title":"Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2504.02398","title":"Scaling Analysis of Interleaved Speech-Text Language Models","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2411.17666","title":"How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2401.14664","title":"UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization","created":"2024-01-26","cited_by_count":8,"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":"2603.12642","title":"Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2311.09117","title":"R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2502.05389","title":"The Role of Prosody in Spoken Question Answering","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2505.15667","title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.22220","title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2306.01916","title":"In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesis","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2307.13423","title":"Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2410.19935","title":"Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2501.06562","title":"Discrete Speech Unit Extraction via Independent Component Analysis","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2509.14882","title":"Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2605.30748","title":"Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2509.00503","title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2509.01390","title":"Analysing the Language of Neural Audio Codecs","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2601.22306","title":"Sylber 2.0: A Universal Syllable Embedding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2609.00727","title":"Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2310.17558","title":"Towards Matching Phones and Speech Representations","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2409.11560","title":"Discrete Unit based Masking for Improving Disentanglement in Voice Conversion","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2501.03711","title":"Unsupervised Speech Segmentation: A General Approach Using Speech Language Models","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2508.11224","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","created":"2025-08-15","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":"2608.31037","title":"Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2409.10969","title":"Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2505.17747","title":"Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2509.09198","title":"GmSLM : Generative Marmoset Spoken Language Modeling","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.12746","title":"Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.31521","title":"UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.09020","title":"Phone Segmentation and Recognition through Phonological Activation Mapping","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}