TCG CREST System Description for the Second DISPLACE Challenge

2024-09-16 · Nikhil Raghav, Subhajit Saha, Md Sahidullah, Swagatam Das

In this report, we describe the speaker diarization (SD) and language diarization (LD) systems developed by our team for the Second DISPLACE Challenge, 2024. Our contributions were dedicated to Track 1 for SD and Track 2 for LD in multilingual and multi-speaker scenarios. We investigated different speech enhancement techniques, voice activity detection (VAD) techniques, unsupervised domain categorization, and neural embedding extraction architectures. We also exploited the fusion of various embedding extraction models. We implemented our system with the open-source SpeechBrain toolkit. Our final submissions use spectral clustering for both the speaker and language diarization. We achieve about $7\%$ relative improvement over the challenge baseline in Track 1. We did not obtain improvement over the challenge baseline in Track 2.

📄 PDF Abstract BibTeX arXiv:2409.15356

Code (0)

등록된 구현이 없습니다.

Tasks

Action Detection Activity Detection speaker-diarization Speaker Diarization Speech Enhancement

Methods 이 논문이 사용한 방법론

Spectral Clustering Spectral clustering has attracted increasing attention due to the promising ability in dealing with nonlinearly separable datasets [15], [16]. In spectral clustering, the…

TCG CREST System Description for the DISPLACE-M Challenge

2026-03-02 · Nikhil Raghav, Md Sahidullah arxiv

This report presents the TCG CREST system description for Track 1 (Speaker Diarization) of the DISPLACE-M challenge, focusing on naturalistic medical conversations in noisy rural-healthcare scenarios. Our study evaluates…

Speaker Diarization Activity Detection

KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models

2026-05-13 · Richard Sproat, Stefano Peluchetti arxiv

Kamon (family crests) are an important part of Japanese culture and a natural test case for compositional visual recognition: each crest combines a small number of symbolic choices, but the space of possible descriptions…

CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding

2026-05-09 · Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan, Md. Tanvir Alam 외 arxiv

Selecting informative frames from long videos is a combinatorial problem that existing methods address either through efficient heuristics without explicit modeling of query-conditioned temporal structure, or through mul…

CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning

2024-04-15 · Haojian Huang, Xiaozhen Qiao, Zhuo Chen, Haodong Chen 외

Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in iden…

Attribute Transfer Learning Visual Localization Zero-Shot Learning

CREST: A Joint Framework for Rationalization and Counterfactual Text Generation

2023-05-26 · Marcos Treviso, Alexis Ross, Nuno M. Guerreiro, André F. T. Martins

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these meth…

counterfactual Data Augmentation Text Generation valid