MOSS 语音转录与说话人识别技术报告
MOSS Transcribe Diarize Technical Report
AI总结：
MOSS转录与识别通过端到端多模态大语言模型，实现了说话人属性化和时间戳化的转录，解决了现有系统在上下文窗口、长距离说话人记忆和时间戳输出方面的不足。
摘要：
说话人属性化、时间戳化的转录（SATS）旨在转录所说的内容，并精确确定每个说话人的时间，这在会议转录中特别有价值。现有的SATS系统很少采用端到端的公式，并且进一步受到有限的上下文窗口、弱的长距离说话人记忆和无法输出时间戳的限制。为了解决这些限制，我们提出了MOSS转录与识别，这是一个统一的多模态大语言模型，以端到端的方式联合执行说话人属性化、时间戳化的转录。在大量真实野外数据上进行训练，并配备了128k的上下文窗口，可以处理长达90分钟的输入，MOSS转录与识别具有良好的扩展性和稳健的泛化能力。在全面的评估中，它在多个公开和内部基准上均优于最先进的商用系统。
英文摘要：
Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
