Ewald van der Westhuizen

An Architectural Scheme for Real-Time Multiple Users Beam Tracking Systems

In this paper, the design, building, and functioning of a complete communication system with 16 antenna elements, software-defined radio, and beam-tracking capabilities for up to four users is reported. Since the design uses components off the shelf, it is relatively low cost, which makes it feasible to be used in high-volume commercial applications. A key feature is that all digital beamforming and advanced direction-of-arrival tracking algorithms are integrated into one segment—the multiple users beam tracker. Experimental results with regard to system performance, responding time, and efficiency illustrate the effectiveness of the concept.

Automatic Speech Recognition of English-isiZulu Code-switched Speech from South African Soap Operas☆

Abstract We introduce a new English-isiZulu code-switched speech corpus compiled from South African soap opera broadcasts. isiZulu itself is currently under-resourced, and automatic speech recognition is made even more challenging by the high prevalence of code-switching in spontaneous speech. Analysis of the corpus reflects effects common in conversational isiZulu, such as vowel deletion and cross-language prefixes and suffixes. Baseline monolingual and code-switched automatic speech recognition systems are developed, including a new language model configuration that explicitly includes switching transitions. For code-switched speech, a system with language-dependent acoustic models and language-dependent language models linked by switching transitions leads to best performance, although word error rates overall remain very high.

A digitally beam-steerable antenna array system for positioning-based tracking applications

In line-of-sight airborne applications, deployment of a steerable antenna array with higher directivity and gain makes sense for reducing ground-station complexity and cost, while still maintaining a reasonable link budget. This paper reports on the design, development, and successful testing of a digitally beam-steerable phased-array antenna integrated as a complete system, comprising the antenna, hosting platform, ground station, and aircraft-based emulator to facilitate convenient aircraft-based testing of the antenna array and ground-air space communication link. Based on the measurements, the 4 × 4 element prototype tested reduced the error rate by a factor of seven in comparison with a 4 × 4 array without steering. For the same link quality, the power required was 12 dB lower than in the case of a single-element antenna. With only minor modifications, the concept can even be used in a Low Earth Orbit (LEO) satellite environment.

Synthesised bigrams using word embeddings for code-switched ASR of four South African language pairs

Abstract Code-switching is the phenomenon whereby multilingual speakers spontaneously alternate between more than one language during discourse and is widespread in multilingual societies. Current state-of-the-art automatic speech recognition (ASR) systems are optimised for monolingual speech, but performance degrades severely when presented with multiple languages. We address ASR of speech containing switches between English and four South African Bantu languages. No comparable study on code-switched speech for these languages has been conducted before and consequently no directly applicable benchmarks exist. A new and unique corpus containing 14.3 hours of spontaneous speech extracted from South African soap operas was used to perform our study. The varied nature of the code-switching in this data presents many challenges to ASR. We focus specifically on how the language model can be improved to better model bilingual language switches for English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho. Code-switching examples in the corpus transcriptions were extremely sparse, with the majority of code-switched bigrams occurring only once. Furthermore, differences in language typology between English and the Bantu languages and among the Bantu languages themselves contribute further challenges. We propose a new method using word embeddings trained on text data that is both out-of-domain and monolingual for the synthesis of artificial bilingual code-switched bigrams to augment the sparse language modelling training data. This technique has the particular advantage of not requiring any additional training data that includes code-switching. We show that the proposed approach is able to synthesise valid code-switched bigrams not seen in the training set. We also show that, by augmenting the training set with these bigrams, we are able to achieve notable reductions for all language pairs in the overall perplexity and particularly substantial reductions in the perplexity calculated across a language switch boundary (between 5 and 31%). We demonstrate that the proposed approach is able to reduce the unseen code-switched bigram types in the test sets by up to 20.5%. Finally, we show that the augmented language models achieve reductions in the word error rate for three of the four language pairs considered. The gains were larger for language pairs with disjunctive orthography than for those with conjunctive orthography. We conclude that the augmentation of language model training data with code-switched bigrams synthesised using word embeddings trained on out-of-domain monolingual text is a viable means of improving the performance of ASR for code-switched speech.

The Effect of Postlexical Deletion on Automatic Speech Recognition in Fast Spontaneously Spoken Zulu.

We consider the phenomenon of postlexical deletion in fast spontaneously spoken isiZulu speech and its implication for automatic speech recognition (ASR). Analysis of hand-crafted transcripts of fast spontaneous speech recorded from broadcast media indicates that postlexical deletion, especially of vowels, is common in isiZulu. We show that ASR performance can be increased by inclusion of pronunciation variants that model such deletions. We also apply a sequence modelling approach normally used for grapheme-to-phoneme (G2P) conversion to generate orthography containing synthetic deletions. These synthetically generated contacted words are subsequently used to generate accompanying pronunciations using conventional G2P conversion. We evaluate an ASR system using these synthetically generated pronunciations, and compare it to a baseline system without such variants as well as an oracle system. Augmentation with synthetically generated pronunciations leads to an absolute improvement in word error rate (WER) of 2.36% relative to the baseline. Furthermore, the augmented system performs almost as well as the oracle system, with an absolute difference in WER of 0.38%.