{"total":121,"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":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"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":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"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":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"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":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"area":null},{"id":"2305.10615","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","created":"2023-05-18","cited_by_count":71,"area":null},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66,"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":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","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":"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":"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":"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":"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":"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":"2305.11411","title":"DUB: Discrete Unit Back-translation for Speech Translation","created":"2023-05-19","cited_by_count":18,"area":null},{"id":"2409.20201","title":"AfriHuBERT: A self-supervised speech representation model for African languages","created":"2024-09-30","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":"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":"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":"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":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"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":"2407.15415","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","created":"2024-07-22","cited_by_count":12,"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":"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":"2304.04596","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","created":"2023-04-10","cited_by_count":10,"area":null},{"id":"2310.05513","title":"Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond","created":"2023-10-09","cited_by_count":10,"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":"2405.20410","title":"SeamlessExpressiveLM: Speech Language Model for Expressive Speech-to-Speech Translation with Chain-of-Thought","created":"2024-05-30","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":"2210.14514","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2309.15317","title":"Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning","created":"2023-09-26","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":"2602.05027","title":"AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders","created":"2026-02-04","cited_by_count":8,"area":"mechinterp"},{"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":"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":"2310.03639","title":"Evaluating Self-Supervised Speech Representations for Indigenous American Languages","created":"2023-10-05","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":"2307.08655","title":"Multilingual Speech-to-Speech Translation into Multiple Target Languages","created":"2023-07-17","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":"2411.18217","title":"How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario","created":"2024-11-27","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":"2309.08531","title":"Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokens","created":"2023-09-15","cited_by_count":4,"area":"mllm"},{"id":"2312.15197","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","created":"2023-12-23","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":"2406.14092","title":"Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2409.10103","title":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2509.09174","title":"EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","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":"2307.14502","title":"The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions","created":"2023-07-27","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":"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":"2306.01201","title":"Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models","created":"2023-06-01","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":"2406.00021","title":"CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2409.16654","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","created":"2024-09-25","cited_by_count":2,"area":"mllm"},{"id":"2412.04425","title":"CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing","created":"2024-12-05","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},{"id":"2212.05805","title":"Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2310.17570","title":"DiffS2UT: A Semantic Preserving Diffusion Model for Textless Direct Speech-to-Speech Translation","created":"2023-10-26","cited_by_count":1,"area":"diffusion"},{"id":"2402.15967","title":"Direct Punjabi to English speech translation using discrete units","created":"2024-02-25","cited_by_count":1,"area":null},{"id":"2405.10741","title":"SBAAM! Eliminating Transcript Dependency in Automatic Subtitling","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2406.07330","title":"CTC-based Non-autoregressive Textless Speech-to-Speech Translation","created":"2024-06-11","cited_by_count":1,"area":null},{"id":"2411.19770","title":"Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning","created":"2024-11-29","cited_by_count":1,"area":null}],"next_cursor":"100"}