pith. sign in

arxiv: 2210.03459 · v1 · pith:5762RTQM · submitted 2022-10-07 · eess.AS · cs.CL· cs.SD

Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization

pith:5762RTQMopen to challenge →

classification eess.AS cs.CLcs.SD
keywords modelmulti-channeldiarizationsingle-channeldataknowledgesingle-speech
0
0 comments X
read the original abstract

Due to the high performance of multi-channel speech processing, we can use the outputs from a multi-channel model as teacher labels when training a single-channel model with knowledge distillation. To the contrary, it is also known that single-channel speech data can benefit multi-channel models by mixing it with multi-channel speech data during training or by using it for model pretraining. This paper focuses on speaker diarization and proposes to conduct the above bi-directional knowledge transfer alternately. We first introduce an end-to-end neural diarization model that can handle both single- and multi-channel inputs. Using this model, we alternately conduct i) knowledge distillation from a multi-channel model to a single-channel model and ii) finetuning from the distilled single-channel model to a multi-channel model. Experimental results on two-speaker data show that the proposed method mutually improved single- and multi-channel speaker diarization performances.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.