SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 34467-34475
DOI: 10.1609/aaai.v40i40.40745 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Han Yin und 8 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).
Abstract (Originalsprache)
The Speaker Diarization and Recognition (SDR) task aims to predict ``who spoke when and what'' within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems. Existing SDR systems typically adopt a cascaded framework, combining multiple modules such as speaker diarization (SD) and automatic speech recognition (ASR). The cascaded systems suffer from several limitations, such as error propagation, difficulty in handling overlapping speech, and lack of joint optimization for exploring the synergy between SD and ASR tasks. To address these limitations, we introduce SpeakerLM, a unified multimodal large language model for SDR that jointly performs SD and ASR in an end-to-end manner. Moreover, to facilitate diverse real-world scenarios, we incorporate a flexible speaker registration mechanism into SpeakerLM, enabling SDR under different speaker registration settings. SpeakerLM is progressively developed with a multi-stage training strategy on large-scale real data. Extensive experiments show that SpeakerLM demonstrates strong data scaling capability and generalizability, outperforming state-of-the-art cascaded baselines on both in-domain and out-of-domain public SDR benchmarks. Furthermore, experimental results show that the proposed speaker registration mechanism effectively ensures robust SDR performance of SpeakerLM across diverse speaker registration conditions and varying numbers of registered speakers.
Zitieren
APA
Yin, H., Chen, Y., Deng, C., Cheng, L., Wang, H., Tan, C., Chen, Q., Wang, W., & Li, X. (2026). SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34467-34475. https://doi.org/10.1609/aaai.v40i40.40745
Vancouver
Yin H, Chen Y, Deng C, Cheng L, Wang H, Tan C, et al. SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):34467-34475. doi:10.1609/aaai.v40i40.40745
BibTeX
@article{Yin2026,
author = {Yin, Han and Chen, Yafeng and Deng, Chong and Cheng, Luyao and Wang, Hui and Tan, Chao-Hong and Chen, Qian and Wang, Wen and Li, Xiangang},
title = {SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {40},
pages = {34467--34475},
doi = {10.1609/aaai.v40i40.40745}
}
EUVIMED