{"total":21,"rows":[{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"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":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32,"area":null},{"id":"2110.07840","title":"ESPnet2-TTS: Extending the Edge of TTS Research","created":"2021-10-15","cited_by_count":22,"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":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"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":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"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":"2207.01718","title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2310.16609","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2406.08820","title":"DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage","created":"2024-06-13","cited_by_count":6,"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":"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":"2301.02966","title":"SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain","created":"2023-01-08","cited_by_count":2,"area":null},{"id":"2304.08453","title":"Improving Autoregressive NLP Tasks via Modular Linearized Attention","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2305.12311","title":"i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data","created":"2023-05-21","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":"2502.00374","title":"A Unit-based System and Dataset for Expressive Direct Speech-to-Speech Translation","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2310.09512","title":"Attentive Multi-Layer Perceptron for Non-autoregressive Generation","created":"2023-10-14","cited_by_count":0,"area":null}],"next_cursor":null}