An Empirical Evaluation of Zero Resource Acoustic Unit Discovery
This work addresses the challenge of unsupervised acoustic model training for speech processing in languages without transcribed data, representing an incremental advance in zero-resource methods.
The paper tackles the problem of acoustic unit discovery (AUD) in zero-resource settings by improving acoustic feature representations through unsupervised linear discriminant analysis and multilingual bottleneck features, resulting in significant improvements in AUD efficacy as evaluated on multiple downstream speech applications.
Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. AUD provides an important avenue for unsupervised acoustic model training in a zero resource setting where expert-provided linguistic knowledge and transcribed speech are unavailable. Therefore, to further facilitate zero-resource AUD process, in this paper, we demonstrate acoustic feature representations can be significantly improved by (i) performing linear discriminant analysis (LDA) in an unsupervised self-trained fashion, and (ii) leveraging resources of other languages through building a multilingual bottleneck (BN) feature extractor to give effective cross-lingual generalization. Moreover, we perform comprehensive evaluations of AUD efficacy on multiple downstream speech applications, and their correlated performance suggests that AUD evaluations are feasible using different alternative language resources when only a subset of these evaluation resources can be available in typical zero resource applications.