ResearchSpace
→
Browsing by Subject

Browsing by Subject "Speech recognition"

Now showing items 1-18 of 18

Appropriate baseline values for HMM-based speech recognition

Author: Barnard, E ; Gouws, E ; Wolvaardt, K ; Kleynhans, N Date: Nov 2004 A number of issues realted to the development of speech-recognition systems with Hidden Markov Models (HMM) are discussed. A set of systematic experiments using the HTK toolkit and the TMIT database are used to elucidate matters such as the ... Read more
Basic speech recognition for spoken dialogues

Author: Van Heerden, C ; Barnard, E ; Davel, M Date: Sep 2009 Spoken dialogue systems (SDSs) have great potential for information access in the developing world. However, the realisation of that potential requires the solution of several challenging problems, including the development of sufficiently ... Read more
Channel normalization technique for speech recognition in mismatched conditions

Author: Kleynhans, N ; Barnard, E Date: Nov 2008 The performance of trainable speech-processing systems deteriorates significantly when there is a mismatch between the training and testing data. The data mismatch becomes a dominant factor when collecting speech data for resource scarce ... Read more
Collecting and evaluating speech recognition corpora for 11 South African languages

Author: Badenhorst, J ; Van Heerden, C ; Davel, M ; Barnard, E Date: Aug 2011 The authors describe the Lwazi corpus for automatic speech recognition (ASR), a new telephone speech corpus which contains data from the eleven official languages of South Africa. Because of practical constraints, the amount of speech per ... Read more
Continuous speech recognition with sparse coding

Author: Smit, WJ ; Barnard, E Date: Apr 2009 Sparse coding is an efficient way of coding information. In a sparse code most of the code elements are zero; very few are active. Sparse codes are intended to correspond to the spike trains with which biological neurons communicate. In this ... Read more
Data requirements for speaker independent acoustic models

Author: Badenhorst, JAC ; Davel, M Date: Nov 2008 When developing speech recognition systems in resource-constrained environments, careful design of the training corpus can play an important role in compensating for data scarcity. One of the factors to consider relates to the speaker composition ... Read more
Developing a corpus to verify the performance of a tone labelling algorithm

Author: Raborife, M ; Zerbian, S ; Ewert, S Date: Nov 2011 The authors report on a study that involved the development of a corpus used to verify the performance of two tone labelling algorithms, with one algorithm being an improvement on the other. These algorithms were developed for speech synthesis ... Read more
The effect of network degradation on speech recognition

Author: Joubert, G ; Barnard, E Date: Nov 2005 The authors describe a system, based on open-source tools, that was developed in order to study the effect of network degenerations in Voice-over-Internet-Protocol applications on speech-recognition accuracy. Sophisticated play-out algorithms ... Read more
Effect of speech rate variation on acoustic phone stability in Afrikaans speech recognition

Author: Badenhorst, JAC ; Davel, MH Date: Nov 2007 The authors analyse the effect of speech rate variation on Afrikaans phone stability from an acoustic perspective. Specifically they introduce two techniques for the acoustic analysis of speech rate variation, apply these techniques to an ... Read more
Efficient harvesting of Internet audio for resource-scarce ASR

Author: Davel, MH ; Van Heerden, C ; Kleynhans, N ; Barnard, E Date: Aug 2011 Spoken recordings that have been transcribed for human reading (e.g. as captions for audiovisual material, or to provide alternative modes of access to recordings) are widely available in many languages. Such recordings and transcriptions ... Read more
Implications of Sepedi/English code switching for ASR systems

Author: Modipa, TI ; Davel, MH ; De Wet, Febe Date: Dec 2013 Code switching (the process of switching from one language to another during a conversation) is a common phenomenon in multilingual environments. Where a minority and dominant language coincide, code switching from the minority language to ... Read more
Language modeling for what-with-where on GOOG-411

Author: Van Heerden, C ; Schalkwyk, J ; Strope, B Date: Sep 2009 This paper describes the language modelling (LM) architectures and recognition experiments that enabled support of 'what-with-where' queries on GOOG-411. First the paper compares accuracy trade-offs between a single national business LM for ... Read more
Lwazi II Final Report: Increasing the impact of speech technologies in South Africa

Author: Calteaux, Karen V ; De Wet, Febe ; Moors, C ; Van Niekerk, D ; McAlister, B ; Grover, AS ; Reid, T ; Davel, M ; Barnard, E ; Van Heerden, C Date: Feb 2013 From 2010-2012 the Human Language Technology (HLT) research group of the CSIR Meraka Institute received funding from the Department of Arts and Culture (DAC) for a project entitled Lwazi II: Increasing the impact of speech technologies in ... Read more
Pooling ASR data for closely related languages

Author: Van Heerden, C ; Kleynhans, N ; Barnard, E ; Davel, M Date: May 2010 We describe several experiments that were conducted to assess the viability of data pooling as a means to improve speech-recognition performance for under-resourced languages. Two groups of closely related languages from the Southern Bantu ... Read more
Rapid development of a command and control interface for smart office environments

Author: Ramunyisi, Ndivhuwo S ; Badenhorst, Jacob AC ; Moors, Carmen ; Gumede, Tebogo Date: Sep 2018 Speech-driven command and control is increasingly gaining momentum in the world around us. Using human speech to control appliances in trendy living spaces allows a user to control many appliances remotely. This paper discusses the rapid ... Read more
Speaker-specific variability of phoneme durations

Author: Van Heerden, CJ ; Barnard, E Date: Nov 2007 The durations of phonemes varies for different speakers. To this end, the correlations between phonemes across different speakers are studied and a novel approach to predict unknown phoneme durations from the values of known phoneme durations ... Read more
Towards effective telephone-based delivery of government services

Author: Barnard, E ; Cloete, L ; Patel, Hina M ; Coetzee, L Date: Sep 2003 Government regulations have combined with a tremendous growth in prepaid cellular telephony to bring telephone connectivity to an unprecedented number of South African citizens – thus creating an ideal platform for delivering services to a ... Read more
Utility of spoken dialog systems

Author: Barnard, E ; Plauche, M ; Davel, M Date: Dec 2008 The commercial successes of spoken dialog systems in the developed world provide encouragement for their use in the developing world, where speech could play a role in the dissemination of relevant information in local languages. We investigate ... Read more

Now showing items 1-18 of 18

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

Tel: + 27 12 841 2911
Email: callcentre@csir.co.za

Physical Address
Meiring Naudé Road
Brummeria
Pretoria
South Africa

Postal Address
PO Box 395
Pretoria 0001
South Africa

Social Connect

Resources on this site are free to download and reuse according to associated licensing provision. Please read the terms and conditions of usage of each resource.

Browsing by Subject "Speech recognition"

Browsing by Subject "Speech recognition"

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

Social Connect