화자인식 임베딩 추출기, 음성 및 중첩 감지를 위한 공동 학습: 더 빠르고 효율적인 화자 분할 시스템 구축
본 논문에서는 화자인식 임베딩 추출기, 음성 활동 감지(VAD), 중첩 화자 감지(OSD)를 동시에 수행하는 단일 모델을 제안하여 기존 모듈형 시스템보다 빠르고 효율적인 화자 분할 시스템을 구축하는 방법을 제시합니다.
Joint Training of a Model for Speaker Embedding Extraction, Speech Activity Detection, and Overlapped Speech Detection for Improved Speaker Diarization
This research paper proposes a novel approach to speaker diarization by jointly training a single model to perform speaker embedding extraction, speech activity detection (VAD), and overlapped speech detection (OSD) simultaneously, achieving competitive performance with faster inference time compared to traditional modular systems.
LS-EEND: A Streaming End-to-End Neural Diarization Model for Long-Form Audio with Online Attractor Extraction
This paper introduces LS-EEND, a novel frame-wise streaming end-to-end neural diarization model that excels in processing long-form audio and handling a flexible number of speakers by employing online attractor extraction and a multi-step progressive training strategy.
Mamba vs. Traditional Architectures for Speaker Diarization Using End-to-End Neural and Clustering-Based Pipeline
This research paper introduces a novel speaker diarization system using Mamba, a state-space model, within an end-to-end neural and clustering-based pipeline, demonstrating its superiority over traditional RNN and attention-based models in terms of accuracy and efficiency.
Robust Target-Speaker Voice Activity Detection Tolerant to Speaker Profile Errors
The proposed Profile-Error-Tolerant Target-Speaker Voice Activity Detection (PET-TSVAD) model is robust to speaker profile errors introduced in the first pass diarization, outperforming the existing TS-VAD models on both the VoxConverse and DIHARD-I datasets.
© 2024 by Linnk AI