Creer, Sarah M (2010) Personalising synthetic voices for individuals with severe speech impairment. PhD thesis, University of Sheffield.
Abstract
Speech technology can help individuals with speech disorders to interact more easily. Many individuals with severe speech impairment, due to conditions such as Parkinson's disease or motor neurone disease, use voice output communication aids (VOCAs), which have synthesised or pre-recorded voice output. This voice output effectively becomes the voice of the individual and should therefore represent the user accurately.
Currently available personalisation of speech synthesis techniques require a large amount of data input, which is difficult to produce for individuals with severe speech impairment. These techniques also do not provide a solution for those individuals whose voices have begun to show the effects of dysarthria.
The thesis shows that Hidden Markov Model (HMM)-based speech synthesis is a promising approach for 'voice banking' for individuals before their condition causes deterioration of the speech and once deterioration has begun. Data input requirements for building personalised voices with this technique using human listener judgement evaluation is investigated. It shows that 100 sentences is the minimum required to build a significantly different voice from an average voice model and show some resemblance to the target speaker. This amount depends on the speaker and the average model used.
A neural network analysis trained on extracted acoustic features revealed that spectral features had the most influence for predicting human listener judgements of similarity of synthesised speech to a target speaker. Accuracy of prediction significantly improves if other acoustic features are introduced and combined non-linearly.
These results were used to inform the reconstruction of personalised synthetic voices for speakers whose voices had begun to show the effects of their conditions. Using HMM-based synthesis, personalised synthetic voices were built using dysarthric speech showing similarity to target speakers without recreating the impairment in the synthesised speech output.
Metadata
Awarding institution: | University of Sheffield |
---|---|
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Computer Science (Sheffield) The University of Sheffield > Faculty of Science (Sheffield) > Computer Science (Sheffield) |
Identification Number/EthosID: | uk.bl.ethos.522463 |
Depositing User: | EThOS Import Sheffield |
Date Deposited: | 11 Sep 2019 11:59 |
Last Modified: | 11 Sep 2019 11:59 |
Open Archives Initiative ID (OAI ID): | oai:etheses.whiterose.ac.uk:21830 |
Downloads
Thesis
Filename: 522463.pdf
Description: Thesis
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-1_lumberjack
Filename: 3-1_lumberjack.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-2_track86f
Filename: 3-2_track86f.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-3_part33_klat
Filename: 3-3_part33_klatt.au
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-4_part35_dectal
Filename: 3-4_part35_dectalk.au
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-5_time-10_35am
Filename: 3-5_time-10_35am.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-6_intro_fest
Filename: 3-6_intro_fest.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-7_original_smc
Filename: 3-7_original_smc.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-8_fest_cupoftea
Filename: 3-8_fest_cupoftea.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-9_mt_cupoftea
Filename: 3-9_mt_cupoftea.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-10_sp1_arctic_a0586
Filename: 3-10_sp1_arctic_a0586.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-11_bad_fest
Filename: 3-11_bad_fest.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-12_sp1_fest
Filename: 3-12_sp1_fest.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
3-13_hts_cupoftea
Filename: 3-13_hts_cupoftea.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
4-1_sp5_a0251
Filename: 4-1_sp5_a0251.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-1_sp1_arctic_a0183
Filename: 5-1_sp1_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-2_sp2_arctic_a0290
Filename: 5-2_sp2_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-3_ave_test_arctic_a0183
Filename: 5-3_ave_test_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-4_sp1_10_test_arctic_a0183
Filename: 5-4_sp1_10_test_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-5_sp1_100_test_arctic_a0183
Filename: 5-5_sp1_100_test_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-6_sp1_500_test_arctic_a0183
Filename: 5-6_sp1_500_test_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-7_sp1_target_test_arctic_a0183
Filename: 5-7_sp1_target_test_arctic_a0183.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-8_ave_test_arctic_a0290
Filename: 5-8_ave_test_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-9_sp2_10_test_arctic_a0290
Filename: 5-9_sp2_10_test_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-10_sp2_100_test_arctic_a0290
Filename: 5-10_sp2_100_test_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-11_sp2_500_test_arctic_a0290
Filename: 5-11_sp2_500_test_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
5-12_sp2_target_test_arctic_a0290
Filename: 5-12_sp2_target_test_arctic_a0290.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-1_sp3_arctic_a0064
Filename: 6-1_sp3_arctic_a0064.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-2_sp4_arctic_a0050
Filename: 6-2_sp4_arctic_a0050.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-3_sp5_arctic_a0359
Filename: 6-3_sp5_arctic_a0359.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-4_sp5_allfeats
Filename: 6-4_sp5_allfeats.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-5_sp5_edited_allfeats
Filename: 6-5_sp5_edited_allfeats.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-6_peter_acapela_short
Filename: 6-6_peter_acapela_short.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-7_sp3_3_scribe_sent013
Filename: 6-7_sp3_3_scribe_sent013.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-8_sp4_3_scribe_sent019
Filename: 6-8_sp4_3_scribe_sent019.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-9_sp5_3_scribe_sent088
Filename: 6-9_sp5_3_scribe_sent088.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-10_sp5_9_scribe_sent088
Filename: 6-10_sp5_9_scribe_sent088.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-11_sp3_5_scribe_sent013
Filename: 6-11_sp3_5_scribe_sent013.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-12_sp4_5_scribe_sent019
Filename: 6-12_sp4_5_scribe_sent019.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-13_sp3_6A_scribe_sent013
Filename: 6-13_sp3_6A_scribe_sent013.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-14_sp4_6A_scribe_sent019
Filename: 6-14_sp4_6A_scribe_sent019.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
6-15_sp5_6A_scribe_sent088
Filename: 6-15_sp5_6A_scribe_sent088.mp3
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
thesis_sound_files.
Filename: thesis_sound_files.html
Licence:
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.5 License
Export
Statistics
You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.