{"total":211,"rows":[{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771,"area":null},{"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":"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":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153,"area":null},{"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":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"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":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"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":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81,"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":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"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":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50,"area":null},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49,"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":"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":"2211.04508","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","created":"2022-11-08","cited_by_count":35,"area":null},{"id":"2205.12523","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","created":"2022-05-25","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":"2312.01479","title":"OpenVoice: Versatile Instant Voice Cloning","created":"2023-12-03","cited_by_count":32,"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":"2202.07359","title":"textless-lib: a Library for Textless Spoken Language Processing","created":"2022-02-15","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":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27,"area":null},{"id":"2309.00169","title":"RepCodec: A Speech Representation Codec for Speech Tokenization","created":"2023-08-31","cited_by_count":27,"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":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","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":"2110.06280","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2303.01664","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","created":"2023-03-03","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":"2305.12464","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","created":"2023-05-21","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":"2312.08676","title":"SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention","created":"2023-12-14","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":"2406.12998","title":"Coding Speech through Vocal Tract Kinematics","created":"2024-06-18","cited_by_count":18,"area":null},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","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":"2211.13282","title":"Voice-preserving Zero-shot Multiple Accent Conversion","created":"2022-11-23","cited_by_count":17,"area":null},{"id":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"area":null},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"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":"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":"2302.08137","title":"ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2111.02674","title":"Voice Conversion Can Improve ASR in Very Low-Resource Settings","created":"2021-11-04","cited_by_count":14,"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":"2307.15064","title":"Self-Supervised Visual Acoustic Matching","created":"2023-07-27","cited_by_count":14,"area":null},{"id":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"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":"2310.01128","title":"Disentangling Voice and Content with Self-Supervision for Speaker Recognition","created":"2023-10-02","cited_by_count":13,"area":null},{"id":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12,"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":"2112.09382","title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","created":"2021-12-17","cited_by_count":11,"area":null},{"id":"2210.06007","title":"JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE","created":"2022-10-12","cited_by_count":11,"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":"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":"2408.10096","title":"Convert and Speak: Zero-shot Accent Conversion with Minimum Supervision","created":"2024-08-19","cited_by_count":11,"area":null},{"id":"2203.15447","title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2208.10497","title":"Are disentangled representations all you need to build speaker anonymization systems?","created":"2022-08-22","cited_by_count":10,"area":null},{"id":"2211.11960","title":"Disentangled Feature Learning for Real-Time Neural Speech Coding","created":"2022-11-22","cited_by_count":10,"area":null},{"id":"2304.04596","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2304.11976","title":"Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2406.00976","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer","created":"2024-06-03","cited_by_count":10,"area":null},{"id":"2406.06937","title":"A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2505.02707","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","created":"2025-05-05","cited_by_count":10,"area":null},{"id":"2207.04356","title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","created":"2022-07-10","cited_by_count":9,"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":"2307.16171","title":"HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer","created":"2023-07-30","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":"2409.06109","title":"Estimating the Completeness of Discrete Speech Units","created":"2024-09-09","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":"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":"2210.14514","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2212.11377","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","created":"2022-12-21","cited_by_count":8,"area":null},{"id":"2401.08095","title":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment","created":"2024-01-16","cited_by_count":8,"area":null},{"id":"2401.09802","title":"Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation","created":"2024-01-18","cited_by_count":8,"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":"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":"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}],"next_cursor":"100"}