Speaker conditioned acoustic modeling for multi-speaker conversational ASR
SR Chetupalli, S Ganapathy - arXiv preprint arXiv:2104.01882, 2021 - arxiv.org
In this paper, we propose a novel approach for the transcription of speech conversations
with natural speaker overlap, from single channel speech recordings. The proposed model …
with natural speaker overlap, from single channel speech recordings. The proposed model …
[PDF][PDF] A Quick and Effective Speaker Diarization System.
Z Chen, L He - Odyssey, 2022 - isca-archive.org
Abstract Currently, Agglomerative Hierarchical Clustering with Variational Bayes Hidden
Markov Model re-clustering (AHCVBHMM) and spectral clustering (SC) are two dominant …
Markov Model re-clustering (AHCVBHMM) and spectral clustering (SC) are two dominant …