{"total":15,"rows":[{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"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":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2509.14882","title":"Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2603.05887","title":"Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2508.04946","title":"REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2603.11578","title":"Streaming Translation and Transcription Through Speech-to-Text Causal Alignment","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2609.09263","title":"Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2603.16924","title":"SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.09916","title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.16026","title":"Conditioned in Training, Dispensable at Inference: Typological Conditioning for Multilingual Speech Translation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.13121","title":"NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2609.30416","title":"All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}