2017/02/05 by Chunxi Liu, Jinyi Yang, Liu, Chunxi +18
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Natural Language Processing Techniques #Speech Recognition and Synthesis #cs.CL
paper · pdf · doi:10.48550/arxiv.1702.01360
5 pages, 1 figure; Accepted for publication at ICASSP 2017
arxiv created 2017/02/05 · openalex publication_date 2017/02/05 · arxiv updated 2017/02/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.