The declared speech separation survey claims a systematic four-part synthesis with fair benchmark comparisons, but its body is not present in the supplied text, so the claims could not be verified.
Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In this paper, we introduce a novel semi-supervised learning framework for end-to-end speech separation. The proposed method first uses mixtures of unseparated sources and the mixture invariant training (MixIT) criterion to train a teacher model. The teacher model then estimates separated sources that are used to train a student model with standard permutation invariant training (PIT). The student model can be fine-tuned with supervised data, i.e., paired artificial mixtures and clean speech sources, and further improved via model distillation. Experiments with single and multi channel mixtures show that the teacher-student training resolves the over-separation problem observed in the original MixIT method. Further, the semisupervised performance is comparable to a fully-supervised separation system trained using ten times the amount of supervised data.
fields
cs.SD 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Advances in Speech Separation: Techniques, Challenges, and Future Trends
The declared speech separation survey claims a systematic four-part synthesis with fair benchmark comparisons, but its body is not present in the supplied text, so the claims could not be verified.