Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels
This addresses speaker verification challenges in data-scarce languages and noisy channels, but is incremental as it builds on existing domain adaptation techniques.
The paper tackled domain adaptation for speaker verification when source data is unavailable and target data is scarce, investigating language and channel mismatches; it evaluated fine-tuning methods with limited labeled target data and proposed an iterative cluster-learn algorithm for unlabeled datasets, showing competitive performance in noisy conditions.
Domain adaptation is often hampered by exceedingly small target datasets and inaccessible source data. These conditions are prevalent in speech verification, where privacy policies and/or languages with scarce speech resources limit the availability of sufficient data. This paper explored techniques of sourcefree domain adaptation unto a limited target speech dataset for speaker verificationin data-scarce languages. Both language and channel mis-match between source and target were investigated. Fine-tuning methods were evaluated and compared across different sizes of labeled target data. A novel iterative cluster-learn algorithm was studied for unlabeled target datasets.