arXiv subjects

Thomas Niesler

Publications and source records attributed to Thomas Niesler.

29 records · Page 2Linked to original sources

arXiv2019

Semi-supervised acoustic model training for five-lingual code-switched ASR

This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The first constructs separate bilingual acoustic models corresponding to language pairs (English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho). The second constructs a single unified five-lingual acoustic model representing all the languages (English, isiZulu, isiXhosa, Setswana and Sesotho). For these two approaches we consider the effectiveness of semi-supervised training to increase the size of the very sparse acoustic training sets. Using approximately 11 hours of untranscribed speech, we show that both approaches benefit from semi-supervised training. The bilingual TDNN-F acoustic models also benefit from the addition of CNN layers (CNN-TDNN-F), while the five-lingual system does not show any significant improvement. 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. Nevertheless, the five-lingual model offers flexibility because it can process more than two languages simultaneously, and is therefore an attractive option as an automatic transcription system in a semi-supervised training pipeline.

cs.CL↗

arXiv2019

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. Such quickly-deployable systems aim to support United Nations (UN) humanitarian relief efforts in parts of Africa with severely under-resourced languages. Our objective is to identify acoustic features that provide acceptable KWS performance in such environments. As supervised resource, we restrict ourselves to a small, easily acquired and independently compiled set of isolated keywords. For feature extraction, a multilingual bottleneck feature (BNF) extractor, trained on well-resourced out-of-domain languages, is integrated with a correspondence autoencoder (CAE) trained on extremely sparse in-domain data. On their own, BNFs and CAE features are shown to achieve a more than 2% absolute performance improvement over baseline MFCCs. However, by using BNFs as input to the CAE, even better performance is achieved, with a more than 11% absolute improvement in ROC AUC over MFCCs and more than twice as many top-10 retrievals for two evaluated languages, English and Luganda. We conclude that integrating BNFs with the CAE allows both large out-of-domain and sparse in-domain resources to be exploited for improved ASR-free keyword spotting.

eess.AS↗

arXiv2019

Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training

We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support humanitarian relief programmes in rural Africa. Using just 1.57 hours of annotated speech data as a seed corpus, we increase the pool of training data by applying semi-supervised training to 17.55 hours of untranscribed speech. We make use of factorised time-delay neural networks (TDNN-F) for acoustic modelling, since these have recently been shown to be effective in resource-scarce situations. Three semi-supervised training passes were performed, where the decoded output from each pass was used for acoustic model training in the subsequent pass. The automatic transcriptions from the best performing pass were used for language model augmentation. To ensure the quality of automatic transcriptions, decoder confidence is used as a threshold. The acoustic and language models obtained from the semi-supervised approach show significant improvement in terms of WER and perplexity compared to the baseline. Incorporating the automatically generated transcriptions yields a 6.55\% improvement in language model perplexity. The use of 17.55 hour of Somali acoustic data in semi-supervised training shows an improvement of 7.74\% relative over the baseline.

cs.CL↗

arXiv2018

Direction of Arrival Estimation of Wide-band Signals with Planar Microphone Arrays

An approach to the estimation of the Direction of Arrival (DOA) of wide-band signals with a planar microphone array is presented. Our algorithm estimates an unambiguous DOA using a single planar array in which the microphones are placed fairly close together and the sound source is expected to be in the far field. The algorithm uses the ambiguous DOA estimates obtained from microphone pairs in the array to determine an unambiguous DOA estimate for the array as a whole. The required pair-wise DOAs may be calculated using Time Delay Estimations (TDEs), which may in turn be calculated using cross-correlation, making the algorithm suitable for wide-band signals. No a priori knowledge of the true Sound Source Location (SSL) is required. Simulations show that the algorithm is robust against noise in the input data. An average ratio of approximately 3:1 exists between the input DOA errors and the output DOA error. Field tests with a moving sound source provided DOA estimates with standard deviations between 20.4 and 15.2 degrees.

cs.SD↗

arXiv2018

Feature Trajectory Dynamic Time Warping for Clustering of Speech Segments

Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is applied as a similarity measure in the agglomerative hierarchical clustering of speech segments. Experiments using MFCC and PLP parametrisations extracted from TIMIT and from the Spoken Arabic Digit Dataset (SADD) show consistent and statistically significant improvements in the quality of the resulting clusters in terms of F-measure and normalised mutual information (NMI).

cs.SD↗

arXiv2018

Cluster Size Management in Multi-Stage Agglomerative Hierarchical Clustering of Acoustic Speech Segments

Agglomerative hierarchical clustering (AHC) requires only the similarity between objects to be known. This is attractive when clustering signals of varying length, such as speech, which are not readily represented in fixed-dimensional vector space. However, AHC is characterised by $O(N^2)$ space and time complexity, making it infeasible for partitioning large datasets. This has recently been addressed by an approach based on the iterative re-clustering of independent subsets of the larger dataset. We show that, due to its iterative nature, this procedure can sometimes lead to unchecked growth of individual subsets, thereby compromising its effectiveness. We propose the integration of a simple space management strategy into the iterative process, and show experimentally that this leads to no loss in performance in terms of F-measure while guaranteeing that a threshold space complexity is not breached.

cs.LG↗

arXiv2018

Non-linear model and optimization method for a single-axis linear-motion energy harvester for footstep excitation

We propose and develop an electrical and mechanical system model of a single-axis linear-motion kinetic energy harvester for impulsive excitation that allows its generated load power to be numerically optimised as a function of design parameters. The device consists of an assembly of one or more spaced magnets suspended by a magnetic spring and passing through one or more coils when motion is experienced along the axis. The design parameters that can be optimised include the number of coils, the coil height, coil spacing, the number of magnets, the magnet spacing and the physical size. We use the proposed model to design optimal energy harvesters for the case of impulse-like motion like that experienced when attached to the leg of a human. We generate several optimised designs, ranked in terms of their predicted load power output. The three best designs are subsequently constructed and subjected to controlled practical evaluation while attached to the leg of a human subject. The results show that the ranking of the measured output power corresponds to the ranking predicted by the optimisation, and that the numerical model correctly Predicts the relative differences in generated power for complex motion. It is also found that all three designs far outperform a baseline design. The best energy harvesters generated an average power of 3.01mW into a 40$Ω$ test load when driven by footsteps whose measured peak impact was approximately 2.2g. With respect to the device dimensions, this corresponds to a power density of 179.380$μ\text{W/cm}^3$.

physics.app-ph↗

arXiv2018

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. This contrasts with related prior work which focuses on the recognition of CS speech in bilingual scenarios. Recently, we have compiled a small five-language corpus of South African soap opera speech which contains examples of CS between 5 languages occurring in various contexts such as using English as the matrix language and switching to other indigenous languages. The ASR system presented in this work is trained on 4 corpora containing English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho CS speech. The interpolation of multiple language models trained on these language pairs enables the ASR system to hypothesize mixed word sequences from these 5 languages. We evaluate various state-of-the-art acoustic models trained on this 5-lingual training data and report ASR accuracy and language recognition performance on the development and test sets of the South African multilingual soap opera corpus.

cs.CL↗

arXiv2018

ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages

We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes) as exemplars for dynamic time warping (DTW) template matching, which is performed on a much larger body of untranscribed speech. These DTW costs are used as targets for a convolutional neural network (CNN) keyword spotter, giving a much faster system than direct DTW. Here we consider how available data from well-resourced languages can improve this CNN-DTW approach. We show that multilingual BNFs trained on ten languages improve the area under the ROC curve of a CNN-DTW system by 10.9% absolute relative to the MFCC baseline. By combining low-resource DTW-based supervision with information from well-resourced languages, CNN-DTW is a competitive option for low-resource keyword spotting.

cs.CL↗

arXiv2018

Automatic Speech Recognition for Humanitarian Applications in Somali

We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We evaluate several types of acoustic model, including recent neural architectures. Language model data augmentation using a combination of recurrent neural networks (RNN) and long short-term memory neural networks (LSTMs) as well as the perturbation of acoustic data are also considered. We find that both types of data augmentation are beneficial to performance, with our best system using a combination of convolutional neural networks (CNNs), time-delay neural networks (TDNNs) and bi-directional long short term memory (BLSTMs) to achieve a word error rate of 53.75%.

cs.CL↗

arXiv2018

Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring

We use dynamic time warping (DTW) as supervision for training a convolutional neural network (CNN) based keyword spotting system using a small set of spoken isolated keywords. The aim is to allow rapid deployment of a keyword spotting system in a new language to support urgent United Nations (UN) relief programmes in parts of Africa where languages are extremely under-resourced and the development of annotated speech resources is infeasible. First, we use 1920 recorded keywords (40 keyword types, 34 minutes of speech) as exemplars in a DTW-based template matching system and apply it to untranscribed broadcast speech. Then, we use the resulting DTW scores as targets to train a CNN on the same unlabelled speech. In this way we use just 34 minutes of labelled speech, but leverage a large amount of unlabelled data for training. While the resulting CNN keyword spotter cannot match the performance of the DTW-based system, it substantially outperforms a CNN classifier trained only on the keywords, improving the area under the ROC curve from 0.54 to 0.64. Because our CNN system is several orders of magnitude faster at runtime than the DTW system, it represents the most viable keyword spotter on this extremely limited dataset.

cs.CL↗