Quantitative room acoustics over a century has accumulated a knowledge base centred around objective acoustic parameters. Realistic and accurate measurements are essential in room acoustics. Occupied measurements are difficult to undertake with current technology, yet it is well established that occupancy changes acoustics. For this reason, new measurement techniques are sought. This thesis concerns anew, machine learning based approach for measuring room acoustic parameters, which is particularly useful for occupied in-situ measurements. A set of artificial neural networks, associated pre-processors and machine learning regimes are developed to extract Reverberation Time (RT), Early Decay Time (EDT) and Speech Transmission Index (STI) from received speech signals. Utilising naturalistic sounds - speech - as excitations, the developed methods circumvent the use of unpleasant noisy test signals and therefore measurements can be made in occupied spaces in a non-invasive fashion. Given the non-invasive nature and achievable accuracy, the new methods can facilitate occupied measurements, providing an alternative to traditional methods to better quantify acoustics of spaces where speech communication is important. Much of the development work of the neural network methods focuses on the preprocessors which produce data reduced and pre-conditioned signals for the neural networks. Two different speech scenarios, separate utterances and continuous running speech are considered, leading to the development of four major neural network methods: 1. Time domain method to extract RTIEDT from separate utterances. 2. Straightforward FFT method to extract STI from short-time speech. 3. Frequency domain method to extract STI from long-time running speech. 4. Frequency domain method to extract RTIEDT from long-time running speech. These methods are all based on supervised learning. Unsupervised models, representing another important class of neural networks, are also investigated in the context of this study and are found useful as pre-processors. The model development and validations are carried out through computer simulations. Results show that better than O.ls and 0.02 resolutions in reverberation time and STI extractions are achievable based on a "one-net-one-speech" machine learning regime: a neural network trains on a particular anechoic speech to extract a designated objective parameter under the excitation of that speech. Neural network systems extracting acoustic parameters from received arbitrary speech signals without using prior knowledge of the speech stimuli, termed source independent measurements, are explored. Although the achieved accuracy is not as good as that of the standard methods and the developed neural network methods on the one-net-one-speech basis, the source independent extraction is potentially more useful in practical systems. Improving the accuracy of the source independent measurements and extending the developed methods to music signals are seemingly the most significant further work of this study.

No description available.

No description available.

Tese de mestrado integrado. Engenharia Civil (Construções Civis). Faculdade de Engenharia. Universidade do Porto. 2012

The aim of this study was to assess the validity of an objective method of speech intelligibility, the Rapid Speech Transmission Index (RASTI), in elementary school classrooms, The RASTI can be obtained more quickly than subjective measures of speech intelligibility and has been shown to be highly valid with adult listeners in auditoriums. In this study RASTI values were correlated with scores on a subjective test of speech intelligibility, the word intelligibility by Picture Identification (WIPI) test, for 45 students in two elementary classrooms (grades 1 through 3 and grade5). Results indicated that the RASTI value is a poor predictor of subjective speech intelligibility (WIPI) scores for these students. There was no significant difference between the correlations obtained in the two classrooms or between the correlations obtained with the average and largest of the three RASTI values and the WIPI scores. Further study needs to be done to determine the applicability of the RASTI to classroom environments.

Tese de Mestrado Integrado. Engenharia Civil (Área de Especialização em Construções). Faculdade de Engenharia. Universidade do Porto. 2012

Speech intelligibility of voice alarm communication systems is extremely important for proper notification and direction of building occupants. Currently, there is no minimum standard to which all voice alarm communication systems must be held. Tests were conducted to determine how system and room characteristics, and the addition of occupants, affect the intelligibility of a voice signal. This research outlines a methodology for measuring the speech intelligibility of a room and describes the impact of numerous variables on these measurements. Eight variables were considered for this study: speaker quantity and location, speaker power tap, sound pressure level (SPL), number and location of occupants, presence of furniture, location of intelligibility measurements, data collection method, and floor covering. All room characteristics had some affect on the room intelligibility; the sound pressure level of the signal and the number and location of occupants had the greatest overall impact on the intelligibility of the room. It is recommended, based on the results of this study, that further investigation be conducted in the following areas: floor finishes, speaker directivity, various population densities, furniture packages and room sizes.

Ljudberikelser används ofta i kontorsmiljöer för att göra det mer behagligt att arbeta genom att sänka taluppfattningsförmågan, i framför allt kontor med öppen planlösning. (Page, 2020). Traditionellt sett så har dessa ljudberikelser bestått av olika typer av brus för att höja bakgrundsnivån i kontoret. Vi tittar på ljudberikelse, inte ur en ingenjörsperspektiv, utan ur ett ljuddesignperspektiv och hur vi kan använda våra kunskaper och erfarenhet för att driva frågan om hur vi kan skapa en mer avsiktligt designad arbetsmiljö i kontor. I den här arbetet så undersöker vi hur en designer kan utnyttja verktyg som symbolism och legatomusik till att skapa en ljudberikelse för en kontorsmiljö. Detta för att skapa en tydlig struktur och ge en stadig grund för framtida ljuddesigners att designa en ljudmiljö som är mer behaglig för kontorsarbetare. I det teoretiska ramverket så tar vi upp relevant forskning som visar att denna vinkel på design av ljudberikelse har en vetenskaplig och etablerad grund. Med denna forskning så har vi utvecklat en metod med en tydlig struktur för hur en ljudberikelse till kontorsmiljöer kan designas, och hur designen kan vara så tillfredsställande som möjligt för ens specifika målgrupp. / Sound enrichment is often used in office environments to make it more comfortable for work by lowering speech intelligibility, primarily in open plan offices. (Page, 2020). Traditionally these sound enrichments have consisted of different types of noise to heighten the background noise in the office. We look at sound enrichment, not through the perspective of an engineer, but through the perspective of sound designers and how we can use our knowledge and experience to drive the question of how we create a more intentionally designed work environment in an office. In this work we investigate how a designer can utilize tools like symbolism and legato music in order to create a sound enrichment for an office environment. We do this in order to create a clear structure and solid groundwork for future sound designers to design a sound environment that is more pleasant for the office workers. In the theoretical framework we will bring forth relevant research that shows how this angle of design of sound enrichment has a scientific and established foundation. With this research we have developed a method with a clear structure for how a sound enrichment for office environments can be designed, and how the design can be as satisfying as possible for a specifically targeted group.