The development of linguistic data, especially annotated corpora, is imperative for the human language technology enablement of any language. The annotation process is, however, often time-consuming and expensive. As such, various projects make use of several strategies to expedite the development of human language technology resources. For resource-scarce languages – those with limited resources, finances and expertise – the efficiency of these strategies has not been conclusively established. This study investigates the efficiency of some of these strategies in the development of resources for resource-scarce languages, in order to provide recommendations for future projects facing decisions regarding which strategies they should implement. For all experiments, Afrikaans is used as an example of a resource-scarce language. Two tasks, viz. lemmatisation of text data and orthographic transcription of audio data, are evaluated in terms of quality and in terms of the time required to perform the task. The main focus of the study is on the skill level of the annotators, software environments which aim to improve the quality and time needed to perform annotations, and whether it is beneficial to annotate more data, or to increase the quality of the data. We outline and conduct systematic experiments on each of the three focus areas in order to determine the efficiency of each. First, we investigated the influence of a respondent’s skill level on data annotation by using untrained, sourced respondents for annotation of linguistic data for Afrikaans. We compared data annotated by experts, novices and laymen. From the results it was evident that the experts outperformed the non-experts on both tasks, and that the differences in performance were statistically significant. Next, we investigated the effect of software environments on data annotation to determine the benefits of using tailor-made software as opposed to general-purpose or domain-specific software. The comparison showed that, for these two specific projects, it was beneficial in terms of time and quality to use tailor-made software rather than domain-specific or general-purpose software. However, in the context of linguistic annotation of data for resource-scarce languages, the additional time needed to develop tailor-made software is not justified by the savings in annotation time. Finally, we compared systems trained with data of varying levels of quality and quantity, to determine the impact of quality versus quantity on the performance of systems. When comparing systems trained with gold standard data to systems trained with more data containing a low level of errors, the systems trained with the erroneous data were statistically significantly better. Thus, we conclude that it is more beneficial to focus on the quantity rather than on the quality of training data. Based on the results and analyses of the experiments, we offer some recommendations regarding which of the methods should be implemented in practice. For a project aiming to develop gold standard data, the highest quality annotations can be obtained by using experts to double-blind annotate data in tailor-made software (if provided for in the budget or if the development time can be justified by the savings in annotation time). For a project that aims to develop a core technology, experts or trained novices should be used to single-annotate data in tailor-made software (if provided for in the budget or if the development time can be justified by the savings in annotation time). / PhD (Linguistics and Literary Theory), North-West University, Potchefstroom Campus, 2014

The development of linguistic data, especially annotated corpora, is imperative for the human language technology enablement of any language. The annotation process is, however, often time-consuming and expensive. As such, various projects make use of several strategies to expedite the development of human language technology resources. For resource-scarce languages – those with limited resources, finances and expertise – the efficiency of these strategies has not been conclusively established. This study investigates the efficiency of some of these strategies in the development of resources for resource-scarce languages, in order to provide recommendations for future projects facing decisions regarding which strategies they should implement. For all experiments, Afrikaans is used as an example of a resource-scarce language. Two tasks, viz. lemmatisation of text data and orthographic transcription of audio data, are evaluated in terms of quality and in terms of the time required to perform the task. The main focus of the study is on the skill level of the annotators, software environments which aim to improve the quality and time needed to perform annotations, and whether it is beneficial to annotate more data, or to increase the quality of the data. We outline and conduct systematic experiments on each of the three focus areas in order to determine the efficiency of each. First, we investigated the influence of a respondent’s skill level on data annotation by using untrained, sourced respondents for annotation of linguistic data for Afrikaans. We compared data annotated by experts, novices and laymen. From the results it was evident that the experts outperformed the non-experts on both tasks, and that the differences in performance were statistically significant. Next, we investigated the effect of software environments on data annotation to determine the benefits of using tailor-made software as opposed to general-purpose or domain-specific software. The comparison showed that, for these two specific projects, it was beneficial in terms of time and quality to use tailor-made software rather than domain-specific or general-purpose software. However, in the context of linguistic annotation of data for resource-scarce languages, the additional time needed to develop tailor-made software is not justified by the savings in annotation time. Finally, we compared systems trained with data of varying levels of quality and quantity, to determine the impact of quality versus quantity on the performance of systems. When comparing systems trained with gold standard data to systems trained with more data containing a low level of errors, the systems trained with the erroneous data were statistically significantly better. Thus, we conclude that it is more beneficial to focus on the quantity rather than on the quality of training data. Based on the results and analyses of the experiments, we offer some recommendations regarding which of the methods should be implemented in practice. For a project aiming to develop gold standard data, the highest quality annotations can be obtained by using experts to double-blind annotate data in tailor-made software (if provided for in the budget or if the development time can be justified by the savings in annotation time). For a project that aims to develop a core technology, experts or trained novices should be used to single-annotate data in tailor-made software (if provided for in the budget or if the development time can be justified by the savings in annotation time). / PhD (Linguistics and Literary Theory), North-West University, Potchefstroom Campus, 2014

The languages spoken in developing countries are diverse and most are currently under-resourced from an automatic speech recognition (ASR) perspective. In South Africa alone, 10 of the 11 official languages belong to this category. Given the potential for future applications of speech-based information systems such as spoken dialog system (SDSs) in these countries, the design of minimal ASR audio corpora is an important research area. Specifically, current ASR systems utilise acoustic models to represent acoustic variability, and effective ASR corpus design aims to optimise the amount of relevant variation within training data while minimising the size of the corpus. Therefore an investigation of the effect that different amounts and types of training data have on these models is needed. With this dissertation specific consideration is given to the data sufficiency principals that apply to the training of acoustic models. The investigation of this task lead to the following main achievements: 1) We define a new stability measurement protocol that provides the capability to view the variability of ASR training data. 2) This protocol allows for the investigation of the effect that various acoustic model complexities and ASR normalisation techniques have on ASR training data requirements. Specific trends with regard to the data requirements for different phone categories and how these are affected by various modelling strategies are observed. 3) Based on this analysis acoustic distances between phones are estimated across language borders, paving the way for further research in cross-language data sharing. Finally the knowledge obtained from these experiments is applied to perform a data sufficiency analysis of a new speech recognition corpus of South African languages: The Lwazi ASR corpus. The findings correlate well with initial phone recognition results and yield insight into the sufficient number of speakers required for the development of minimal telephone ASR corpora. / Thesis (M. Ing. (Computer and Electronical Engineering))--North-West University, Potchefstroom Campus, 2009.

In the world of human language technology, resource–scarce languages (RSLs) suffer from the problem of little available electronic data and linguistic expertise. The Lwazi project in South Africa is a large–scale endeavour to collect and apply such resources for all eleven of the official South African languages. One of the deliverables of the project is more natural text–to–speech (TTS) voices. Naturalness is primarily determined by prosody and it is shown that many aspects of prosodic modelling is, in turn, dependent on part–of–speech (POS) information. Solving the POS problem is, therefore, a prudent first step towards meeting the goal of natural TTS voices. In a resource–scarce environment, obtaining and applying the POS information are not trivial. Firstly, an automatic tagger is required to tag the text to be synthesised with POS categories, but state–of–the–art POS taggers are data–driven and thus require large amounts of labelled training data. Secondly, the subsequent processes in TTS that are used to apply the POS information towards prosodic modelling are resource–intensive themselves: some require non–trivial linguistic knowledge; others require labelled data as well. The first problem asks the question of which available POS tagging algorithm will be the most accurate on little training data. This research sets out to answer the question by reviewing the most popular supervised data–driven algorithms. Since literature to date consists mostly of isolated papers discussing one algorithm, the aim of the review is to consolidate the research into a single point of reference. A subsequent experimental investigation compares the tagging algorithms on small training data sets of English and Afrikaans, and it is shown that the hidden Markov model (HMM) tagger outperforms the rest when using both a comprehensive and a reduced POS tagset. Regarding the second problem, the question arises whether it is perhaps possible to circumvent the traditional approaches to prosodic modelling by learning the latter directly from the speech data using POS information. In other words, does the addition of POS features to the HTS context labels improve the naturalness of a TTS voice? Towards answering this question, HTS voices are trained from English and Afrikaans prosodically rich speech. The voices are compared with and without POS features incorporated into the HTS context labels, analytically and perceptually. For the analytical experiments, measures of prosody to quantify the comparisons are explored. It is then also noted whether the results of the perceptual experiments correlate with their analytical counterparts. It is found that, when a minimal feature set is used for the HTS context labels, the addition of POS tags does improve the naturalness of the voice. However, the same effect can be accomplished by including segmental counting and positional information instead of the POS tags. / Thesis (M.Sc. Engineering Sciences (Electrical and Electronic Engineering))--North-West University, Potchefstroom Campus, 2011.

The languages spoken in developing countries are diverse and most are currently under-resourced from an automatic speech recognition (ASR) perspective. In South Africa alone, 10 of the 11 official languages belong to this category. Given the potential for future applications of speech-based information systems such as spoken dialog system (SDSs) in these countries, the design of minimal ASR audio corpora is an important research area. Specifically, current ASR systems utilise acoustic models to represent acoustic variability, and effective ASR corpus design aims to optimise the amount of relevant variation within training data while minimising the size of the corpus. Therefore an investigation of the effect that different amounts and types of training data have on these models is needed. With this dissertation specific consideration is given to the data sufficiency principals that apply to the training of acoustic models. The investigation of this task lead to the following main achievements: 1) We define a new stability measurement protocol that provides the capability to view the variability of ASR training data. 2) This protocol allows for the investigation of the effect that various acoustic model complexities and ASR normalisation techniques have on ASR training data requirements. Specific trends with regard to the data requirements for different phone categories and how these are affected by various modelling strategies are observed. 3) Based on this analysis acoustic distances between phones are estimated across language borders, paving the way for further research in cross-language data sharing. Finally the knowledge obtained from these experiments is applied to perform a data sufficiency analysis of a new speech recognition corpus of South African languages: The Lwazi ASR corpus. The findings correlate well with initial phone recognition results and yield insight into the sufficient number of speakers required for the development of minimal telephone ASR corpora. / Thesis (M. Ing. (Computer and Electronical Engineering))--North-West University, Potchefstroom Campus, 2009.

In the world of human language technology, resource–scarce languages (RSLs) suffer from the problem of little available electronic data and linguistic expertise. The Lwazi project in South Africa is a large–scale endeavour to collect and apply such resources for all eleven of the official South African languages. One of the deliverables of the project is more natural text–to–speech (TTS) voices. Naturalness is primarily determined by prosody and it is shown that many aspects of prosodic modelling is, in turn, dependent on part–of–speech (POS) information. Solving the POS problem is, therefore, a prudent first step towards meeting the goal of natural TTS voices. In a resource–scarce environment, obtaining and applying the POS information are not trivial. Firstly, an automatic tagger is required to tag the text to be synthesised with POS categories, but state–of–the–art POS taggers are data–driven and thus require large amounts of labelled training data. Secondly, the subsequent processes in TTS that are used to apply the POS information towards prosodic modelling are resource–intensive themselves: some require non–trivial linguistic knowledge; others require labelled data as well. The first problem asks the question of which available POS tagging algorithm will be the most accurate on little training data. This research sets out to answer the question by reviewing the most popular supervised data–driven algorithms. Since literature to date consists mostly of isolated papers discussing one algorithm, the aim of the review is to consolidate the research into a single point of reference. A subsequent experimental investigation compares the tagging algorithms on small training data sets of English and Afrikaans, and it is shown that the hidden Markov model (HMM) tagger outperforms the rest when using both a comprehensive and a reduced POS tagset. Regarding the second problem, the question arises whether it is perhaps possible to circumvent the traditional approaches to prosodic modelling by learning the latter directly from the speech data using POS information. In other words, does the addition of POS features to the HTS context labels improve the naturalness of a TTS voice? Towards answering this question, HTS voices are trained from English and Afrikaans prosodically rich speech. The voices are compared with and without POS features incorporated into the HTS context labels, analytically and perceptually. For the analytical experiments, measures of prosody to quantify the comparisons are explored. It is then also noted whether the results of the perceptual experiments correlate with their analytical counterparts. It is found that, when a minimal feature set is used for the HTS context labels, the addition of POS tags does improve the naturalness of the voice. However, the same effect can be accomplished by including segmental counting and positional information instead of the POS tags. / Thesis (M.Sc. Engineering Sciences (Electrical and Electronic Engineering))--North-West University, Potchefstroom Campus, 2011.

Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. In this thesis we present research into developing techniques and tools to (1) harvest audio data, (2) rapidly adapt ASR systems and (3) select “useful” training samples in order to assist with resource-scarce ASR system development. We demonstrate an automatic audio harvesting approach which efficiently creates a speech recognition corpus by harvesting an easily available audio resource. We show that by starting with bootstrapped acoustic models, trained with language data obtain from a dialect, and then running through a few iterations of an alignment-filter-retrain phase it is possible to create an accurate speech recognition corpus. As a demonstration we create a South African English speech recognition corpus by using our approach and harvesting an internet website which provides audio and approximate transcriptions. The acoustic models developed from harvested data are evaluated on independent corpora and show that the proposed harvesting approach provides a robust means to create ASR resources. As there are many acoustic model adaptation techniques which can be implemented by an ASR system developer it becomes a costly endeavour to select the best adaptation technique. We investigate the dependence of the adaptation data amount and various adaptation techniques by systematically varying the adaptation data amount and comparing the performance of various adaptation techniques. We establish a guideline which can be used by an ASR developer to chose the best adaptation technique given a size constraint on the adaptation data, for the scenario where adaptation between narrow- and wide-band corpora must be performed. In addition, we investigate the effectiveness of a novel channel normalisation technique and compare the performance with standard normalisation and adaptation techniques. Lastly, we propose a new data selection framework which can be used to design a speech recognition corpus. We show for limited data sets, independent of language and bandwidth, the most effective strategy for data selection is frequency-matched selection and that the widely-used maximum entropy methods generally produced the least promising results. In our model, the frequency-matched selection method corresponds to a logarithmic relationship between accuracy and corpus size; we also investigated other model relationships, and found that a hyperbolic relationship (as suggested from simple asymptotic arguments in learning theory) may lead to somewhat better performance under certain conditions. / Thesis (PhD (Computer and Electronic Engineering))--North-West University, Potchefstroom Campus, 2013.

Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. In this thesis we present research into developing techniques and tools to (1) harvest audio data, (2) rapidly adapt ASR systems and (3) select “useful” training samples in order to assist with resource-scarce ASR system development. We demonstrate an automatic audio harvesting approach which efficiently creates a speech recognition corpus by harvesting an easily available audio resource. We show that by starting with bootstrapped acoustic models, trained with language data obtain from a dialect, and then running through a few iterations of an alignment-filter-retrain phase it is possible to create an accurate speech recognition corpus. As a demonstration we create a South African English speech recognition corpus by using our approach and harvesting an internet website which provides audio and approximate transcriptions. The acoustic models developed from harvested data are evaluated on independent corpora and show that the proposed harvesting approach provides a robust means to create ASR resources. As there are many acoustic model adaptation techniques which can be implemented by an ASR system developer it becomes a costly endeavour to select the best adaptation technique. We investigate the dependence of the adaptation data amount and various adaptation techniques by systematically varying the adaptation data amount and comparing the performance of various adaptation techniques. We establish a guideline which can be used by an ASR developer to chose the best adaptation technique given a size constraint on the adaptation data, for the scenario where adaptation between narrow- and wide-band corpora must be performed. In addition, we investigate the effectiveness of a novel channel normalisation technique and compare the performance with standard normalisation and adaptation techniques. Lastly, we propose a new data selection framework which can be used to design a speech recognition corpus. We show for limited data sets, independent of language and bandwidth, the most effective strategy for data selection is frequency-matched selection and that the widely-used maximum entropy methods generally produced the least promising results. In our model, the frequency-matched selection method corresponds to a logarithmic relationship between accuracy and corpus size; we also investigated other model relationships, and found that a hyperbolic relationship (as suggested from simple asymptotic arguments in learning theory) may lead to somewhat better performance under certain conditions. / Thesis (PhD (Computer and Electronic Engineering))--North-West University, Potchefstroom Campus, 2013.

When working in the terrain of text processing, metadata about a particular text plays an important role. Metadata is often generated using automatic text classification systems which classifies a text into one or more predefined classes or categories based on its contents. One of the dimensions by which a text can be can be classified, is the genre of a text. In this study the development of an automatic genre classification system in a resource scarce environment is postulated. This study aims to: i) investigate the techniques and approaches that are generally used for automatic genre classification systems, and identify the best approach for Afrikaans (a resource scarce language), ii) transfer this approach to other indigenous South African resource scarce languages, and iii) investigate the effectiveness of technology recycling for closely related languages in a resource scarce environment. To achieve the first goal, five machine learning approaches were identified from the literature that are generally used for text classification, together with five common approaches to feature extraction. Two different approaches to the identification of genre classes are presented. The machine learning-, feature extraction- and genre class identification approaches were used in a series of experiments to identify the best approach for genre classification for a resource scarce language. The best combination is identified as the multinomial naïve Bayes algorithm, using a bag of words approach as features to classify texts into three abstract classes. This results in an f-score (performance measure) of 0.929 and it was subsequently shown that this approach can be successfully applied to other indigenous South African languages. To investigate the viability of technology recycling for genre classification systems for closely related languages, Dutch test data was classified using an Afrikaans genre classification system and it is shown that this approach works well. A pre-processing step was implemented by using a machine translation system to increase the compatibility between Afrikaans and Dutch by translating the Dutch texts before classification. This results in an f-score of 0.577, indicating that technology recycling between closely related languages has merit. This approach can be used to promote and fast track the development of genre classification systems in a resource scarce environment. / MA (Linguistics and Literary Theory), North-West University, Potchefstroom Campus, 2013

When working in the terrain of text processing, metadata about a particular text plays an important role. Metadata is often generated using automatic text classification systems which classifies a text into one or more predefined classes or categories based on its contents. One of the dimensions by which a text can be can be classified, is the genre of a text. In this study the development of an automatic genre classification system in a resource scarce environment is postulated. This study aims to: i) investigate the techniques and approaches that are generally used for automatic genre classification systems, and identify the best approach for Afrikaans (a resource scarce language), ii) transfer this approach to other indigenous South African resource scarce languages, and iii) investigate the effectiveness of technology recycling for closely related languages in a resource scarce environment. To achieve the first goal, five machine learning approaches were identified from the literature that are generally used for text classification, together with five common approaches to feature extraction. Two different approaches to the identification of genre classes are presented. The machine learning-, feature extraction- and genre class identification approaches were used in a series of experiments to identify the best approach for genre classification for a resource scarce language. The best combination is identified as the multinomial naïve Bayes algorithm, using a bag of words approach as features to classify texts into three abstract classes. This results in an f-score (performance measure) of 0.929 and it was subsequently shown that this approach can be successfully applied to other indigenous South African languages. To investigate the viability of technology recycling for genre classification systems for closely related languages, Dutch test data was classified using an Afrikaans genre classification system and it is shown that this approach works well. A pre-processing step was implemented by using a machine translation system to increase the compatibility between Afrikaans and Dutch by translating the Dutch texts before classification. This results in an f-score of 0.577, indicating that technology recycling between closely related languages has merit. This approach can be used to promote and fast track the development of genre classification systems in a resource scarce environment. / MA (Linguistics and Literary Theory), North-West University, Potchefstroom Campus, 2013