Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 7 of 7 for “"Under-resourced languages"”.

  1. Effective automatic speech recognition data collection for underresourced languages

    As building transcribed speech corpora for under-resourced languages plays a pivotal role in developing automatic speech recognition (ASR) technologies for such languages, a key step in developing these technologies is the effective collection of ASR data, consisting of transcribed audio and …

    nwu-za Repository record for Effective automatic speech recognition data collection for under–resourced languages (opens in a new tab)

  2. Recurrent neural network language models in the context of under-resourced South African languages

    … these triumphs have been concentrated in languages with significant resources such as large datasets. Thus, many languages, which are commonly referred to as under-resourced languages, have received little attention and have yet to benefit from recent advances. This investigation aims to …

    cape-town Repository record for Recurrent neural network language models in the context of under-resourced South African languages (opens in a new tab)

  3. Unsupervised learning of cross-modal mappings between speech and text

    … state-of-the-art speech recognition algorithm to under-resourced languages infeasible. In this thesis, we propose a general framework for mapping sequences between speech and text. Each component in this framework can be trained without any labeled data so the entire framework is unsupervised. We …

    mit Repository record for Unsupervised learning of cross-modal mappings between speech and text (opens in a new tab)

  4. Representation Learning beyond Semantic Similarity: Character-aware and Function-specific Approaches

    … processing (NLP) concerned with building machine-understandable representations of discrete units of text. Continuous representations are at the core of modern machine learning applications, and representation learning has thereby become one of the central research areas in NLP. The induction of …

    cambridge Repository record for Representation Learning beyond Semantic Similarity: Character-aware and Function-specific Approaches (opens in a new tab)

  5. Acquiring and Harnessing Verb Knowledge for Multilingual Natural Language Processing

    … an unsupervised fashion. However, this signal is underused in downstream tasks, where they tend to fall back on superficial cues and heuristics to solve the problem at hand. Further progress relies on identifying and filling the gaps in linguistic knowledge captured in their parameters. The …

    cambridge Repository record for Acquiring and Harnessing Verb Knowledge for Multilingual Natural Language Processing (opens in a new tab)

  6. Feasibility of individualised synthetic speech for children with complex communication needs in three South African languages (South African English, Afrikaans, and isiXhosa)

    … these challenges, ensuring a comprehensive understanding of the context. 3) To delineate the process of generating naturalistic synthetic child speech: Tacotron 2, an open-source speech synthesis system, is used for three under resourced languages (South African English/SAE, Afrikaans, and …

    cape-town Repository record for Feasibility of individualised synthetic speech for children with complex communication needs in three South African languages (South African English, Afrikaans, and isiXhosa) (opens in a new tab)

  7. Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning

    Most of the world's languages suffer from the paucity of annotated data. This curbs the effectiveness of supervised learning, the most widespread approach to modelling language. Instead, an alternative paradigm could take inspiration from the propensity of children to acquire language from limited …

    cambridge Repository record for Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning (opens in a new tab)