-
Neural Speaker Diarization for Unlimited Number of Speakers Using End-to-End ...
This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). -
The AMI Corpus: A Spoken Language Corpus for Speaker Diarization and Emotion ...
The AMI corpus: A spoken language corpus for speaker diarization and emotion recognition -
End-to-End Neural Speaker Diarization with Permutation-Free Objectives
The End-to-End Neural Speaker Diarization dataset is a benchmark for speaker diarization. -
The Third DIHARD Diarization Challenge
The DIHARD dataset is a benchmark for speaker diarization. -
Speaker Diarization with LSTM
Speaker diarization is the process of partitioning an input audio stream into homogeneous segments according to the speaker identity. -
Speaker Diarisation Using 2D Self-Attentive Combination of Embeddings
Speaker diarisation systems often cluster audio segments using speaker embeddings such as i-vectors and d-vectors. This paper proposes a generic framework to improve performance... -
Probabilistic embeddings for speaker diarization
Speaker embeddings (x-vectors) extracted from very short segments of speech have recently been shown to give competitive performance in speaker diarization. We generalize this...
