# CASA-ASR: Context-Aware Speaker-Attributed ASR

arXiv: https://arxiv.org/abs/2305.12459 · HTML: https://mlsanity.com/paper/2305.12459/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2023.

## Built on by (most cited first, 6 of 6)

- [Advancing Multi-talker ASR Performance with Large Language Models](https://mlsanity.com/paper/2408.17431/) (2024)
- [LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization](https://mlsanity.com/paper/2409.00819/) (2024)
- [MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models](https://mlsanity.com/paper/2411.18152/) (2024)
- [Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio](https://mlsanity.com/paper/2505.10975/) (2025)
- [AG-LSEC: Audio Grounded Lexical Speaker Error Correction](https://mlsanity.com/paper/2406.17266/) (2024)
- [SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models](https://mlsanity.com/paper/2501.08421/) (2025)

## Abstract (arXiv)

Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is employed to model the speaker discriminability by contrasting with speakers in the context. In addition, a two-pass decoding strategy is further proposed to fully leverage the contextual modeling ability resulting in a better recognition performance. Experimental results on AliMeeting corpus show that the proposed CASA-ASR model outperforms the original E2E SA-ASR system with a relative improvement of 11.76% in terms of speaker-dependent character error rate.