# The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge

arXiv: https://arxiv.org/abs/2409.02041 · HTML: https://mlsanity.com/paper/2409.02041/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2024.

## Built on by (most cited first, 5 of 5)

- [Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems](https://mlsanity.com/paper/2409.06656/) (2024)
- [Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder](https://mlsanity.com/paper/2508.20474/) (2025)
- [Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings](https://mlsanity.com/paper/2501.17304/) (2025)
- [SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper](https://mlsanity.com/paper/2601.19194/) (2026)
- [Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics](https://mlsanity.com/paper/2603.22709/) (2026)

## Abstract (arXiv)

This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge. The primary difficulty of this challenge is the dataset recorded across various conference rooms, which captures real-world complexities such as high overlap rates, background noises, a variable number of speakers, and natural conversation styles. To address these issues, we optimized the system in several aspects: For front-end speech signal processing, we introduced a data-driven joint training method for diarization and separation (JDS) to enhance audio quality. Additionally, we also integrated traditional guided source separation (GSS) for multi-channel track to provide complementary information for the JDS. For back-end speech recognition, we enhanced Whisper with WavLM, ConvNeXt, and Transformer innovations, applying multi-task training and Noise KLD augmentation, to significantly advance ASR robustness and accuracy. Our system attained a Time-Constrained minimum Permutation Word Error Rate (tcpWER) of 14.265% and 22.989% on the CHiME-8 NOTSOFAR-1 Dev-set-2 multi-channel and single-channel tracks, respectively.