1,721,016 research outputs found
Engineering of Microbial Fuel Cells technology: Materials, Modelling and Architecture
Full text linkA Microbial fuel cell (MFC) is a bio-electrochemical reactor, able to convert chemical energy, contained in organic substrate, in electrical energy, thanks to the metabolic activity of microorganisms. Firstly, a fluid-dynamic modelling of different Microbial Fuel Cell configurations to study trajectories and concentration profile of the liquid containing the organic substrate during operation of the device was developed. The study of the device was joined with the study and the synthesis of carbon based aerogels to be used as new electrode materials, both for the anode and the cathode. The aim of the modelling was to understand what happen, from a fluid-dynamic point of view, inside the cell during operation. It was based on the application of equations from fluid-dynamics in order to study both the particle trajectories (using Navier-Stokes equations) and diffusion of substrate inside the reactor (using Fick's laws). Three different MFC architecture were investigated, starting from a circular shape. To increase the area of the reactor interested by flux exchange with respect to the one in the circular configuration, a new a squared MFC, with a non-alignment of the inlet and the outlet was proposed. Starting from results obtained during the simulation for the squared reactor, to accommodate the flux distribution, a further improvement in architecture was introduced: a drop-shape MFC, with a percentage of fluid area exchanged, higher than 96%. Another possibility to improve MFC performances, is the optimization of materials used as electrodes. To be an efficient electrode, a material must satisfy some important condition: biocompatibility, good electrically conductivity, resistance to electrolytic solutions and high surface area together with high porosity to allow the formation of the biofilm. Carbon based aerogels can satisfy all these properties. Organic aerogels were synthetized following a green approach, starting from marine polysaccharides, like agar and starch and then transformed in carbon based, thanks to a thermal process. The synthesis procedure is the sol-gel technique, followed by a drying process that can extract the liquid part of the gel, leaving the solid structure, without collapse the material. Synthetized materials were analyzed both structurally and morphologically in order to understand if porosity, surface area and chemical composition were appropriate. To enhance some of these properties, a post synthesis treatment was performed: the surface of the aerogel was treated with a KOH solution in order to enlarge pores and increase the porosity of the overall material. The optimized aerogel was tested, as anode, into the square shape MFC and compared with commercial carbon material having the same function. Due to their high surface area, high porosity and good interaction with microorganisms, aerogels presented better performances of commercial materials if used as anode in MFC. Considering, instead, the addition of amino acids as nitrogen source to the previous material, it allowed the used of polysaccharide aerogel, as cathode electrode able to catalyze the oxygen reduction reaction (ORR). They were tested in MFC, compared with the most used catalyst material in literature, that is platinum. Another alternative to platinum in the catalysis of the ORR, is represented by the metal oxide aerogels. In this work, aerogels based on MnxOy were tested. The synthesis of this material is similar to the previous one, with the difference of the addition of the manganese oxide directly between initial precursors. Through the thermal process, the organic part of the material is burned, leaving an oxide structure that is active from a catalytic point of view. After the morphological, structural and chemical analysis of the sample, the catalytic activity of the material was tested, as in the previous case, using the Rotating Ring Disk Electrode (RRDE) technique, in order to investigate its catalytic properties
Coping with out-of-vocabulary words: open versus huge vocabulary ASR
No full textThis paper investigates methods for coping with out-of-vocabulary words in a large vocabulary speech recognition task, namely the automatic transcription of Italian broadcast news. Two alternative ways for augmenting a 64K(thousand)-word recognition vocabulary and language model are compared: introducing extra words with their phonetic transcription up to 1.2M (million) words, or extending the language model with so-called graphones, i.e. sub-word units made of phone-character sequences. Graphones and phonetic transcriptions of words are automatically generated by adapting an off-the-shelf statistical machine translation toolkit. We found that the word-based and graphone-based extensions allow both for better recognition performance, with the former performing significantly better than the latter. In addition, the word-based extension approach shows interesting potential even under conditions of little supervision. In fact, by training the grapheme to phoneme translation system with only 2K manually verified transcriptions, the final word error rate increases by just 3% relative, with respect to starting from a lexicon of 64K
Investigating automatic assessment of reading comprehension in young children
No full textThis paper describes a preliminary investigation into automatic assessment of reading comprehension in young children. In particular we studied the feasibility of automatic scoring of answers to open-ended questions related to the contents of a passage read by a child. Data from 70 children in grades 1 and 2 were used in this work. An automatic speech recognition system, especially trained for children`s speech, was used for tracking the read passage, and two methods for automatic assessment were tested and compared with scores assigned by elementary school teachers. Automatic assessment showed a high kappa statistics agreement with evaluation scores obtained from teachers` scores, K=0.62, comparable to the inter-teacher agreement, K=0.64
Preliminary Investigations in Automatic Recognition of English Sentences Uttered by Italian Children
No full textInvestigating Recognition of Children`s Speech
No full textIn this work recognition of children`s speech was investigated by considering a phone recognition task. Two baseline systems were trained, one for childrenand one for adults, by exploiting two Italian speech databases. Under matching conditions, training and recognition performed with data from the same population group, the phone recognition accuracy was 77.30% and 79.43% for children and adults, respectively. It was found that for many children recognition results were as good as for adults. However, for children an higher variability in phone recognition accuracy across speakers was observed, than for adults. Vocal tract length normalization, under matched and mismatched training and testing conditions, was also investigated. For both adults and children a performance improvement, with respect to the baseline systems, was observed
A comparison of read and spontaneous children`s speech recognition
No full textIn this paper, we present a series of phone and word recognition experiments carried out on read and spontaneous speech collected from children. A recognition system was developed exploiting clean read speech, collected from children aged 7-13, and written text. Word recognition experiments were carried out exploiting 4-gram language models with recognition vocabulary of different sizes: 10k, 64k and 1210k words. Phone recognition experiments were carried out by exploiting several n-gram phone language models: 7-gram, 5-gram, 3-gram, 2-gram and phone-loop LMs. Experiments show that very high recognition performance can be achieved on clean read children`s speech (e.g. 6.9% phone error rare). However, performance drops drastically when the system is applied to spontaneous speech collected from children (e.g. 27.2% phone error rate)
Preliminary Investigation in Automatic Recognition of English Sentences Uttered by Italian Children
No full textThis paper reports on a initial research activity in the area of non-native children’s speech recognition that was carried out by exploiting two children databases, one consisting of speech collected from native English children, the other one consisting of English sentences read by Italian learners of English in the same age range of native speech speakers. By exploiting the corpus of native speech a baseline speech recognizer was trained for British English. Recognition results achieved for Italian children uttering the same English texts. Word error rates achieved for Italian children were 100%-600% higher than those achieved for English children of the same age. Adapting baseline acoustic models by using a group of Italian learners of English, resulted in a great improvement in recognition performance on non-native speec
Multiple light scattering and near-field effects in a fractal treelike ensemble of dielectric nanoparticles
No full textSpeaker Normalization through Constrained MLLR Based Transforms
No full textIn this paper, a novel speaker normalization method is presented and compared to a well known vocal tract length normalization method. With this method, acoustic observations of training and testing speakers are mapped into a normalized acoustic space through speaker-specific transformations with the aim of reducing inter-speaker acoustic variability. For each speaker, an affine transformation is estimated with the goal of reducing the mismatch between the acoustic data of the speaker and a set of target hidden Markov models. This transformation is estimated through constrained maximum likelihood linear regression and then applied to map the acoustic observations of the speaker into the normalized acoustic space. Recognition experiments made use of two corpora, the first one consisting of adults` speech, the second one consisting of children`s speech. Performing training and recognition with normalized data resulted in a consistent reduction of the word error rate with respect to the baseline systems trained on unnormalized data. In addition, the novel method always performed better than the reference vocal tract length normalization metho
Speaker Adaptive Acoustic Modeling with Mixture of Adult and Children`s Speech
No full textIn this paper, speaker adaptive acoustic modeling is investigated in the context of large vocabulary speech recognition by training acoustic models with adult speech, children`s speech and a mixture of adult and children`s speech. By exploiting a limited amount (9 hours) of children`s speech and a more significant amount (57 hours) of adult speech, group-specific acoustic models for children and adults, respectively, were trained using several methods for speaker adaptive acoustic modeling. In addition, age-independent acoustic models were trained by exploiting adult and children`s speech. Recognition experiments were performed on three speech corpora, two consisting of children`s speech and one of adult speech, using 64k word and 11k word trigram language models. Methods for speaker adaptive acoustic modeling proved to be effective, in particular for training acoustic models on a mixture of adult and children`s speech, ensuring recognition performance aligned with that achieved with group-specific models for adults and children. A 10.2% word error rate was achieved on speech collected from children in the age range 8-12, compared with the 8.2% word error rate achieved for adults uttering the same texts
- …
