Large-Scale clustering of acoustic segments for sub-word acoustic modelling
Thesis (PhD)--Stellenbosch University, 2019.
ENGLISH ABSTRACT: A pronunciation dictionary is one of the key building blocks in automatic speech recognition (ASR) systems. However, pronunciation dictionaries used in state-of-the-art ASR systems are hand-crafted by linguists. This process requires expertise, time and funding and as a consequence is not realised for many under-resourced languages. To address this, we develop a new unsupervised agglomerative hierarchical clustering (AHC) algorithm that can be used to discover sub-word units that can in turn be used for the automatic induction of a pronunciation dictionary. The new algorithm, named multi-stage agglomerative hierarchical clustering (MAHC), addresses the O(N2) memory and computation complexity observed when classical AHC is applied to large datasets. MAHC splits the data into independent subsets and applies AHC to each. The resultant clusters are merged, re-divided into subsets, and passed to a following iteration. Results show that MAHC can match and even surpass the performance of classical AHC. Furthermore, MAHC can automatically determine the optimal number of clusters which is a feature not offered by most other approaches. A further refinement of MAHC, termed MAHC with memory size management (MAHC+M), addresses the case where some subsets may exhibit excessive growth during iterative clustering. MAHC+M is able to adhere to maximum memory constraints, which improves efficiency and is practically useful when using parallel computing resources. The input to MAHC is a matrix of pairwise distances computed with dynamic time warping (DTW). A modified form of DTW, named feature trajectory DTW (FTDTW), is introduced and shown to generally lead to better performance for both MAHC and MAHC+M. It is shown that clusters obtained using the MAHC algorithm can be used as sub-word units (SWUs) for acoustic modelling. Pronunciations in terms of these SWUs were obtained by alignment with the orthography. Speech recognition experiments show that dictionaries induced using clusters obtained by FTDTW-based MAHC+M consistently outperform those obtained using DTW-based MAHC.