MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization
This addresses the need for accurate, timestamped transcription with speaker identification in meetings, representing a novel end-to-end approach rather than an incremental improvement.
The paper tackles the problem of Speaker-Attributed, Time-Stamped Transcription (SATS) for meeting transcription by introducing MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs transcription and diarization in an end-to-end paradigm, and it outperforms state-of-the-art commercial systems on multiple benchmarks.
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.