{"total":105,"rows":[{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120,"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"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,"area":null},{"id":"2204.02967","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","created":"2022-04-06","cited_by_count":44,"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":"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":"2210.03538","title":"An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era","created":"2022-10-06","cited_by_count":33,"area":null},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"area":null},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32,"area":null},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"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":"2202.07359","title":"textless-lib: a Library for Textless Spoken Language Processing","created":"2022-02-15","cited_by_count":28,"area":null},{"id":"2310.08715","title":"Toward Joint Language Modeling for Speech Units and Text","created":"2023-10-12","cited_by_count":28,"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":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"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":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22,"area":null},{"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,"area":null},{"id":"2511.10262","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2306.02207","title":"SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts","created":"2023-06-03","cited_by_count":21,"area":null},{"id":"2212.04559","title":"SpeechLMScore: Evaluating speech generation using speech language model","created":"2022-12-08","cited_by_count":20,"area":null},{"id":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19,"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":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","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":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2501.04962","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","created":"2025-01-09","cited_by_count":16,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2212.09730","title":"Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","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":"2403.12408","title":"MSLM-S2ST: A Multitask Speech Language Model for Textless Speech-to-Speech Translation with Speaker Style Preservation","created":"2024-03-19","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":"2305.08709","title":"Back Translation for Speech-to-text Translation Without Transcripts","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2310.16334","title":"Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling","created":"2023-10-25","cited_by_count":9,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2410.00025","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2503.10620","title":"From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2508.09350","title":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2305.18096","title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","created":"2023-05-29","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":"2310.12477","title":"Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks","created":"2023-10-19","cited_by_count":5,"area":null},{"id":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2509.23635","title":"MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2303.01261","title":"ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2307.01673","title":"Disentanglement in a GAN for Unconditional Speech Synthesis","created":"2023-07-04","cited_by_count":4,"area":null},{"id":"2406.02315","title":"An Independence-promoting Loss for Music Generation with Language Models","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2505.17446","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2211.06535","title":"A unified one-shot prosody and speaker conversion system with self-supervised discrete speech units","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2305.11438","title":"Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2310.02971","title":"Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2503.12115","title":"Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations","created":"2025-03-15","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":"2601.11329","title":"F-Actor: Controllable Conversational Behaviour in Full-Duplex Models","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2603.16874","title":"Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models","created":"2026-01-27","cited_by_count":3,"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":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2407.12206","title":"A Language Modeling Approach to Diacritic-Free Hebrew TTS","created":"2024-07-16","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":"2605.05927","title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2301.12331","title":"Time out of Mind: Generating Rate of Speech conditioned on emotion and speaker","created":"2023-01-29","cited_by_count":1,"area":null},{"id":"2403.12402","title":"An Empirical Study of Speech Language Models for Prompt-Conditioned Speech Synthesis","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2407.01911","title":"Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2407.17172","title":"Speech Editing -- a Summary","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2410.03192","title":"MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech","created":"2024-10-04","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":"2506.14767","title":"A Variational Framework for Improving Naturalness in Generative Spoken Language Models","created":"2025-06-17","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":"2603.05299","title":"WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.22260","title":"Greater accessibility can amplify discrimination in generative AI","created":"2026-03-23","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":"2607.05251","title":"Privacy-Preserving Robustness Verification for Neural Networks","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.06461","title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2202.01933","title":"Identifying stimulus-driven neural activity patterns in multi-patient intracranial recordings","created":"2022-02-04","cited_by_count":0,"area":null},{"id":"2212.07939","title":"RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis","created":"2022-12-15","cited_by_count":0,"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":"2509.09198","title":"GmSLM : Generative Marmoset Spoken Language Modeling","created":"2025-09-11","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}],"next_cursor":"100"}