Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Large-Scale clustering of acoustic segments for sub-word acoustic modelling
Thesis (PhD)--Stellenbosch University, 2019.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2019
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613963347296256 |
|---|---|
| access_status_str | Open Access |
| author | Lerato, Lerato |
| author2 | Niesler, T. R. |
| author_browse | Lerato, Lerato Niesler, T. R. |
| author_facet | Niesler, T. R. Lerato, Lerato |
| author_sort | Lerato, Lerato |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (PhD)--Stellenbosch University, 2019. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/105757 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:44:29.748Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2019 |
| publishDateRange | 2019 |
| publishDateSort | 2019 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/105757 Large-Scale clustering of acoustic segments for sub-word acoustic modelling Lerato, Lerato Niesler, T. R. Stellenbosch University. Faculty of Engineering. Dept. of Electrical and Electronic Engineering. Large-Scale Clustering; Acoustic Segments; Sub-word; Acoustic Modelling Automatic speech recognition Agglomerations Acoustical engineering UCTD 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. Doctoral 2019-02-01T07:48:22Z 2019-04-17T08:11:43Z 2019-02-01T07:48:22Z 2019-04-17T08:11:43Z 2019-04 Thesis http://hdl.handle.net/10019.1/105757 en_ZA Stellenbosch University 125 pages application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Large-Scale Clustering; Acoustic Segments; Sub-word; Acoustic Modelling Automatic speech recognition Agglomerations Acoustical engineering UCTD Lerato, Lerato Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title | Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title_full | Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title_fullStr | Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title_full_unstemmed | Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title_short | Large-Scale clustering of acoustic segments for sub-word acoustic modelling |
| title_sort | large scale clustering of acoustic segments for sub word acoustic modelling |
| topic | Large-Scale Clustering; Acoustic Segments; Sub-word; Acoustic Modelling Automatic speech recognition Agglomerations Acoustical engineering UCTD |
| url | http://hdl.handle.net/10019.1/105757 |
| work_keys_str_mv | AT leratolerato largescaleclusteringofacousticsegmentsforsubwordacousticmodelling |