Feature set augmentation for enhancing the performance of a non-intrusive quality predictor

Petkov, Petko N.; Helgason, Hannes; Kleijn, W. Bastiaan

doi:10.1109/qomex.2012.6263856

Cited by 1 publication

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As will be explained in Chapter 4, in supervised learning terminology, non-intrusive quality estimation can be described as a multi-class classification or a regression problem, where the input and output are the signal features and the quality score respectively [1]. Several non-intrusive methods have recently been proposed in the context of quality assessment, using machine learning algorithms for estimating the score of audio signals [23,24,25,26,27,28,29,30,31]. Figure (1.1) shows the high-level structure of a non-intrusive quality assessment system.…”

Section: Approaches and Principlesmentioning

confidence: 99%

“…These systems may differ in the considered features, the predicting function, or both. The work de-scribed in [60] makes use of a classifier to predict the discrete value of quality score while the works described in [23,24,25,26,27,28,29,31,61,62] apply regression methods (with shallow architectures) to estimate the subjective Mean Opinion Score (MOS) assigned to a speech file. On the other hand, approaches in [16,30] use a combination of classification and regression algorithms as the predicting function.…”

Section: Relevant Workmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Non-Intrusive Speech Quality Assessment

Hakami¹

View full text Add to dashboard Cite

This thesis presents two studies on non-intrusive speech quality assessment methods. The first applies supervised learning methods to speech quality assessment, which is a common approach in machine learning based quality assessment. To outperform existing methods, we concentrate on enhancing the feature set. In the second study, we analyse quality assessment from a different point of view inspired by the biological brain and present the first unsupervised learning based non-intrusive quality assessment that removes the need for labelled training data. Supervised learning based, non-intrusive quality predictors generally involve the development of a regressor that maps signal features to a representation of perceived quality. The performance of the predictor largely depends on 1) how sensitive the features are to the different types of distortion, and 2) how well the model learns the relation between the features and the quality score. We improve the performance of the quality estimation by enhancing the feature set and using a contemporary machine learning model that fits this objective. We propose an augmented feature set that includes raw features that are presumably redundant. The speech quality assessment system benefits from this redundancy as it results in reducing the impact of unwanted noise in the input. Feature set augmentation generally leads to the inclusion of features that have non-smooth distributions. We introduce a new pre-processing method and re-distribute the features to facilitate the training. The evaluation of the system on the ITU-T Supplement23 database illustrates that the proposed system outperforms the popular standards and contemporary methods in the literature. The unsupervised learning quality assessment approach presented in this thesis is based on a model that is learnt from clean speech signals. Consequently, it does not need to learn the statistics of any corruption that exists in the degraded speech signals and is trained only with unlabelled clean speech samples. The quality has a new definition, which is based on the divergence between 1) the distribution of the spectrograms of test signals, and 2) the pre-existing model that represents the distribution of the spectrograms of good quality speech. The distribution of the spectrogram of the speech is complex, and hence comparing them is not trivial. To tackle this problem, we propose to map the spectrograms of speech signals to a simple latent space. Generative models that map simple latent distributions into complex distributions are excellent platforms for our work. Generative models that are trained on the spectrograms of clean speech signals learned to map the latent variable $Z$ from a simple distribution $P_Z$ into a spectrogram $X$ from the distribution of good quality speech. Consequently, an inference model is developed by inverting the pre-trained generator, which maps spectrograms of the signal under the test, $X_t$, into its relevant latent variable, $Z_t$, in the latent space. We postulate the divergence between the distribution of the latent variable and the prior distribution $P_Z$ is a good measure of the quality of speech. Generative adversarial nets (GAN) are an effective training method and work well in this application. The proposed system is a novel application for a GAN. The experimental results with the TIMIT and NOIZEUS databases show that the proposed measure correlates positively with the objective quality scores.

show abstract

Section: Approaches and Principlesmentioning

confidence: 99%

Section: Relevant Workmentioning

confidence: 99%

Machine Learning for Non-Intrusive Speech Quality Assessment

Hakami¹

View full text Add to dashboard Cite

show abstract

Feature set augmentation for enhancing the performance of a non-intrusive quality predictor

Cited by 1 publication

References 9 publications

Machine Learning for Non-Intrusive Speech Quality Assessment

Machine Learning for Non-Intrusive Speech Quality Assessment

Contact Info

Product

Resources

About