{"total":139,"rows":[{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"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":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167,"area":null},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"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":"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":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"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":"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":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40,"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":"2210.15759","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":"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":"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":"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":"2406.03049","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","created":"2024-06-05","cited_by_count":21,"area":null},{"id":"2203.13339","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","created":"2022-03-24","cited_by_count":20,"area":null},{"id":"2211.00115","title":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","created":"2022-10-31","cited_by_count":19,"area":null},{"id":"2306.02982","title":"PolyVoice: Language Models for Speech to Speech Translation","created":"2023-06-05","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":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2410.08035","title":"IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities","created":"2024-10-09","cited_by_count":17,"area":null},{"id":"2205.12216","title":"T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation","created":"2022-05-24","cited_by_count":16,"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":"2308.07593","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},{"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":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2203.17113","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","created":"2022-03-31","cited_by_count":12,"area":null},{"id":"2205.08993","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","created":"2022-05-18","cited_by_count":12,"area":null},{"id":"2305.17547","title":"Translatotron 3: Speech to Speech Translation with Monolingual Data","created":"2023-05-27","cited_by_count":12,"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":"2401.13463","title":"SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering","created":"2024-01-24","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":"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":"2301.10606","title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation","created":"2023-01-25","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":"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":"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":"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":"2110.08250","title":"Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention","created":"2021-10-15","cited_by_count":9,"area":null},{"id":"2210.17027","title":"Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation","created":"2022-10-31","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":"2310.07403","title":"DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation","created":"2023-10-11","cited_by_count":9,"area":null},{"id":"2312.09781","title":"GSQA: An End-to-End Model for Generative Spoken Question Answering","created":"2023-12-15","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":"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":"2312.06668","title":"Evaluating Self-supervised Speech Models on a Taiwanese Hokkien Corpus","created":"2023-12-06","cited_by_count":7,"area":null},{"id":"2509.21144","title":"UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice","created":"2025-09-25","cited_by_count":7,"area":null},{"id":"2602.11072","title":"Simultaneous Speech-to-Speech Translation Without Aligned Data","created":"2026-02-11","cited_by_count":7,"area":null},{"id":"2305.15403","title":"AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2309.07566","title":"Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2507.07803","title":"StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2307.04123","title":"Towards cross-language prosody transfer for dialog","created":"2023-07-09","cited_by_count":5,"area":null},{"id":"2308.03024","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","created":"2023-08-06","cited_by_count":5,"area":null},{"id":"2402.16021","title":"TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2406.02733","title":"Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2410.03734","title":"Accent conversion using discrete units with parallel data synthesized from controllable accented TTS","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2411.04699","title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2210.11835","title":"A Textless Metric for Speech-to-Speech Comparison","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2305.12552","title":"Wav2SQL: Direct Generalizable Speech-To-SQL Parsing","created":"2023-05-21","cited_by_count":4,"area":null},{"id":"2306.17005","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2405.13233","title":"MELD-ST: An Emotion-aware Speech Translation Dataset","created":"2024-05-21","cited_by_count":4,"area":null},{"id":"2406.05547","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2406.07289","title":"Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2502.00377","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","created":"2025-02-01","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":"2110.08214","title":"From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation","created":"2021-10-15","cited_by_count":3,"area":null},{"id":"2210.16755","title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","created":"2022-10-30","cited_by_count":3,"area":null},{"id":"2305.15405","title":"Textless Speech-to-Speech Translation With Limited Parallel Data","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2306.17199","title":"Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data","created":"2023-06-29","cited_by_count":3,"area":null},{"id":"2309.15826","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","created":"2023-09-27","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":"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":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","cited_by_count":3,"area":null},{"id":"2504.18715","title":"Spatial Speech Translation: Translating Across Space With Binaural Hearables","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2506.10299","title":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2203.00648","title":"Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training","created":"2022-03-01","cited_by_count":2,"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":"2211.11584","title":"Dialogs Re-enacted Across Languages","created":"2022-11-18","cited_by_count":2,"area":null},{"id":"2305.12518","title":"VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2310.07279","title":"Enhancing expressivity transfer in textless speech-to-speech translation","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2404.10268","title":"Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2406.00021","title":"CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2509.18360","title":"Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documents","created":"2025-09-22","cited_by_count":2,"area":null}],"next_cursor":"100"}