Search Results for author:
Found 12 papers, 1 papers with code
Building a Unified Code-Switching ASR System for South African Languages
We present our first efforts towards building a single multilingual automatic speech recognition (ASR) system that can process code-switching (CS) speech in five languages spoken within the same population.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis.
Semi-supervised acoustic model training for five-lingual code-switched ASR
Furthermore, because English is common to all language pairs in our data, it dominates when training a unified language model, leading to improved English ASR performance at the expense of the other languages.
Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training
The automatic transcriptions from the best performing pass were used for language model augmentation.
Feature exploration for almost zero-resource ASR-free keyword spotting using a multilingual bottleneck extractor and correspondence autoencoders
We compare features for dynamic time warping (DTW) when used to bootstrap keyword spotting (KWS) in an almost zero-resource setting.
Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages.
Semi-supervised acoustic and language model training for English-isiZulu code-switched speech recognition
We present an analysis of semi-supervised acoustic and language model training for English-isiZulu code-switched (CS) ASR using soap opera speech.
Semi-supervised Acoustic Modelling for Five-lingual Code-switched ASR using Automatically-segmented Soap Opera Speech
Automatic segmentation was applied in combination with automaticspeaker diarization.
Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages.
Feature learning for efficient ASR-free keyword spotting in low-resource languages
We show that, using these features, the CNN-DTW keyword spotter performs almost as well as the DTW keyword spotter while outperforming a baseline CNN trained only on the keyword templates.
Multilingual training set selection for ASR in under-resourced Malian languages
We find that, although maximising the training pool by including all six additional languages provides improved speech recognition in both target languages, substantially better performance can be achieved by a more judicious choice.
