Adapting speech separation to real-world meetings using mixture invariant training
The recently-proposed mixture invariant training (MixIT) is an unsupervised method for
training single-channel sound separation models because it does not require ground-truth
isolated reference sources. In this paper, we investigate using MixIT to adapt a separation
model on real far-field overlapping reverberant and noisy speech data from the AMI Corpus.
The models are tested on real AMI recordings containing overlapping speech, and are
evaluated subjectively by human listeners. To objectively evaluate our models, we also …
training single-channel sound separation models because it does not require ground-truth
isolated reference sources. In this paper, we investigate using MixIT to adapt a separation
model on real far-field overlapping reverberant and noisy speech data from the AMI Corpus.
The models are tested on real AMI recordings containing overlapping speech, and are
evaluated subjectively by human listeners. To objectively evaluate our models, we also …
Adapting Speech Separation Systems to Real-World Meetings Using Mixture Invariant Training
The recently-proposed mixture invariant training (MixIT) is an unsupervised method for
training single-channel sound separation models in the sense that it does not require
ground-truth isolated reference sources. In this paper, we investigate using MixIT to adapt a
separation model on real far-field overlapping reverberant and noisy speech data from the
AMI Corpus. The models are tested on real AMI recordings containing overlapping speech,
and are evaluated subjectively by human listeners. To objectively evaluate our models, we …
training single-channel sound separation models in the sense that it does not require
ground-truth isolated reference sources. In this paper, we investigate using MixIT to adapt a
separation model on real far-field overlapping reverberant and noisy speech data from the
AMI Corpus. The models are tested on real AMI recordings containing overlapping speech,
and are evaluated subjectively by human listeners. To objectively evaluate our models, we …
Showing the best results for this search. See all results