{"total":18,"rows":[{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"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":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2510.05613","title":"PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction","created":"2025-10-07","cited_by_count":9,"area":null},{"id":"2401.02921","title":"Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2309.14324","title":"Towards General-Purpose Text-Instruction-Guided Voice Conversion","created":"2023-09-25","cited_by_count":6,"area":null},{"id":"2411.14453","title":"Direct Speech-to-Speech Neural Machine Translation: A Survey","created":"2024-11-13","cited_by_count":6,"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":"2410.03798","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2310.02971","title":"Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2505.18517","title":"LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2503.08594","title":"PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2509.22061","title":"Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias","created":"2025-09-26","cited_by_count":0,"area":null}],"next_cursor":null}