{"total":340,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"area":null},{"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":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529,"area":"mllm"},{"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":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"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":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"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":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171,"area":"diffusion"},{"id":"2107.05604","title":"Direct speech-to-speech translation with discrete units","created":"2021-07-12","cited_by_count":149,"area":null},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"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":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119,"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":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98,"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":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"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":"2111.11755","title":"Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance","created":"2021-11-23","cited_by_count":84,"area":"diffusion"},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"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":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72,"area":null},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72,"area":"agents"},{"id":"2404.18886","title":"A Survey on Diffusion Models for Time Series and Spatio-Temporal Data","created":"2024-04-29","cited_by_count":67,"area":"diffusion"},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55,"area":"diffusion"},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"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":"2308.12682","title":"SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge","created":"2023-08-24","cited_by_count":49,"area":null},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47,"area":null},{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47,"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":"2305.11095","title":"Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization","created":"2023-05-18","cited_by_count":43,"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":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"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":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"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":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","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":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30,"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":"2205.15819","title":"Do self-supervised speech models develop human-like perception biases?","created":"2022-05-31","cited_by_count":28,"area":null},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","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":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26,"area":null},{"id":"2210.06175","title":"Exploring Efficient-tuning Methods in Self-supervised Speech Models","created":"2022-10-10","cited_by_count":26,"area":null},{"id":"2211.06474","title":"Speech-to-Speech Translation For A Real-world Unwritten Language","created":"2022-11-11","cited_by_count":25,"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":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"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":"2408.07144","title":"Language Models as Models of Language","created":"2024-08-13","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":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2301.11462","title":"How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2302.04215","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","created":"2023-02-08","cited_by_count":22,"area":null},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22,"area":"diffusion"},{"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":"2505.15406","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","created":"2025-05-21","cited_by_count":21,"area":"safety"},{"id":"2212.04559","title":"SpeechLMScore: Evaluating speech generation using speech language model","created":"2022-12-08","cited_by_count":20,"area":null},{"id":"2203.16773","title":"SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks","created":"2022-03-31","cited_by_count":19,"area":null},{"id":"2310.01088","title":"Towards human-like spoken dialogue generation between AI agents from written dialogue","created":"2023-10-02","cited_by_count":19,"area":"agents"},{"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":"2203.16930","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","created":"2022-03-31","cited_by_count":17,"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":"2305.04572","title":"Putting Natural in Natural Language Processing","created":"2023-05-08","cited_by_count":17,"area":null},{"id":"2510.13632","title":"Closing the Gap Between Text and Speech Understanding in LLMs","created":"2025-10-15","cited_by_count":17,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null}],"next_cursor":"100"}