An empirical evaluation of zero resource acoustic unit discovery

By Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukáš Burget, Sanjeev Khudanpur. 2017

14 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

Citations in the corpus

• Libri-Light: A Benchmark for ASR with Limited or No Supervision (2019, neutral): “While distant supervision has been the focus of two JHU-JSALT workshops (2016 [16], 2019 [17]) but no benchmark has yet emerged.”
• Multilingual bottle-neck feature learning from untranscribed speech (2017, unknown): “Recently there is an increasing research interest in unsupervised speech processing, which usually involves unsupervised discovery of linguistic units [1, 2, 3], and the derived techniques have been used in different applications, such as retrieval of spoken queries in a speech database [4, 5, 6] an”