ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis 文章

ArXiv CS.AI2026-05-27NEWSen作者: Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh Shakery
大语言模型
查看原文 →
关系图谱

ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis · 相关技术

相关技术

ORMODEPLAlanguage model递归自我改进远程代码执行（RCE）text-to-speech (TTS)UCTTTSStraight-Through EstimatorStanScalaSULSSEResourcesReferring expression comprehension (REC)MITIn-context learningGrouped Memorization EvaluationForEffort Metric AttentionASRARGANNICEBERT