Carla Lopes

Phoneme Recognition on the TIMIT Database

In the information age, computer applications have become part of modern life and this has in turn encouraged the expectations of friendly interaction with them. Speech, as “the” communication mode, has seen the successful development of quite a number of applications using automatic speech recognition (ASR), including command and control, dictation, dialog systems for people with impairments, translation, etc. But the actual challenge goes beyond the use of speech in control applications or to access information. The goal is to use speech as an information source, competing, for example, with text online. Since the technology supporting computer applications is highly dependent on the performance of the ASR system, research into ASR is still an active topic, as is shown by the range of research directions suggested in (Baker et al., 2009a, 2009b). Automatic speech recognition – the recognition of the information embedded in a speech signal and its transcription in terms of a set of characters, (Junqua & Haton, 1996) – has been object of intensive research for more than four decades, achieving notable results. It is only to be expected that speech recognition advances make spoken language as convenient and accessible as online text when the recognizers reach error rates near zero. But while digit recognition has already reached a rate of 99.6%, (Li, 2008), the same cannot be said of phone recognition, for which the best rates are still under 80% 1,(Mohamed et al., 2011; Siniscalchi et al., 2007). Speech recognition based on phones is very attractive since it is inherently free from vocabulary limitations. Large Vocabulary ASR (LVASR) systems’ performance depends on the quality of the phone recognizer. That is why research teams continue developing phone recognizers, in order to enhance their performance as much as possible. Phone recognition is, in fact, a recurrent problem for the speech recognition community. Phone recognition can be found in a wide range of applications. In addition to typical LVASR systems like (Morris & Fosler-Lussier, 2008; Scanlon et al., 2007; Schwarz, 2008), it can be found in applications related to keyword detection, (Schwarz, 2008), language recognition, (Matejka, 2009; Schwarz, 2008), speaker identification, (Furui, 2005) and applications for music identification and translation, (Fujihara & Goto, 2008; Gruhne et al., 2007). The challenge of building robust acoustic models involves applying good training algorithms to a suitable set of data. The database defines the units that can be trained and

Insulin and IGF-1 regularize energy metabolites in neural cells expressing full-length mutant huntingtin

Huntingtons disease (HD) is an autosomal dominant neurodegenerative disorder linked to the expression of mutant huntingtin. Bioenergetic dysfunction has been described to contribute to HD pathogenesis. Thus, treatment paradigms aimed to ameliorate energy deficits appear to be suitable candidates in HD. In previous studies, we observed protective effects of insulin growth factor-1 (IGF-1) in YAC128 and R6/2 mice, two HD mouse models, whereas IGF-1 and/or insulin halted mitochondrial-driven oxidative stress in mutant striatal cells and mitochondrial dysfunction in HD human lymphoblasts. Here, we analyzed the effect of IGF-1 versus insulin on energy metabolic parameters using striatal cells derived from HD knock-in mice and primary cortical cultures from YAC128 mice. STHdh(Q111/Q111) cells exhibited decreased ATP/ADP ratio and increased phosphocreatine levels. Moreover, pyruvate levels were increased in mutant cells, most probably in consequence of a decrease in pyruvate dehydrogenase (PDH) protein expression and increased PDH phosphorylation, reflecting its inactivation. Insulin and IGF-1 treatment significantly decreased phosphocreatine levels, whereas IGF-1 only decreased pyruvate levels in mutant cells. In a different scenario, primary cortical cultures derived from YAC128 mice also displayed energetic abnormalities. We observed a decrease in both ATP/ADP and phosphocreatine levels, which were prevented following exposure to insulin or IGF-1. Furthermore, decreased lactate levels in YAC128 cultures occurred concomitantly with a decline in lactate dehydrogenase activity, which was ameliorated with both insulin and IGF-1. These data demonstrate differential HD-associated metabolic dysfunction in striatal cell lines and primary cortical cultures, both of which being alleviated by insulin and IGF-1.

Revisiting Mitochondrial Function and Metabolism in Pluripotent Stem Cells: Where Do We Stand in Neurological Diseases?

Pluripotent stem cells (PSCs) are powerful cellular tools that can generate all the different cell types of the body, and thus overcome the often limited access to human disease tissues; this becomes highly relevant when aiming to investigate cellular (dys)function in diseases affecting the central nervous system. Recent studies have demonstrated that PSC and differentiated cells show altered mitochondrial function and metabolic profiles and production of reactive oxygen species. This raises an emerging paradigm about the role of mitochondria in stem cell biology and urges the need to identify mitochondrial pathways involved in these processes. In this respect, this review focuses on the metabolic profile of PSC and how mitochondrial function can influence the reprogramming and differentiation processes. Indeed, both embryonic stem cells (ESCs) and induced pluripotent stem cells (iPSCs) favor the glycolytic pathway as a major source of energy production over oxidative phosphorylation. PSC mitochondria are characterized by a spherical shape, low copy number of mitochondrial DNA, and a hyperpolarized state. Indeed, mitochondria appear to have a crucial role in reprogramming iPSC, in the maintenance of a pluripotent state, and in differentiation. Moreover, an increase in mitochondrial oxidative phosphorylation has to occur for differentiation to succeed. Therefore, in vitro differentiation of neural stem cells (NSCs) into neurons can be compromised if those mechanisms are impaired. Future research should shed light on how mitochondrial impairment occurring in pre differentiation neural stages (e.g., in NSC or premature neurons) may contribute for the etiopathogenesis of neurodevelopmental and neurological disorders.

Development of a Speech Recognizer with the Tecnovoz Database

This paper describes the development of a robust speech recognition using a database collected in the scope of the Tecnovoz project. The speech recognition system is speaker independent, robust to noise and operates in a small footprint embedded hardware platform. Some issues about the database, the training of the acoustic models, the noise suppression front-end and the recognizers confidence measure are addressed in the paper. Although the database was especially designed for specific small-vocabulary tasks, the best system performance was obtained using triphone models rather than whole-word models.

Acoustic Similarity Scores for Keyword Spotting

This paper presents a study on keyword spotting systems based on acoustic similarity between a filler model and keyword model. The ratio between the keyword model likelihood and the generic (filler) model likelihood is used by the classifier to detect relevant peaks values that indicate keyword occurrences. We have changed the standard scheme of keyword spotting system to allow keyword detection in a single forward step. We propose a new log-likelihood ratio normalization to minimize the effect of word length on the classifier performance. Tests show the effectiveness of our normalization method against two other methods. Experiments were performed on continuous speech utterances of the Portuguese TECNOVOZ database (read sentences) with keywords of several lengths.

A european portuguese children speech database for computer aided speech therapy

This paper introduces a European Portuguese speech database containing spoken material recorded from children. The need for such database arose from the need of train phone models for the development of a computer aided speech therapy system. Articulatory disorders affect a significant number of children in pre-school age. We propose a system intended to assist and reinforce the conventional speech therapy programs. Through the systematic use of games, it learns the phones where the child has more difficulty to pronounce. The child is then taken to train the production of those phones by playing games. Another interest of a children speech database is that accurate childrens phone recognition is only possible using training data that reflects the population of users. It is a difficult task due to the high pitch of childrens speech.

Event Detection by HMM, SVM and ANN: A Comparative Study

The goal of speech event detection (SED) is to reveal the presence of important elements in the speech signal for different sound classes. In a speech recognition system, events can be combined to detect phones, words or sentences, or to identify landmarks with which a decoder could be synchronized. In this paper, we introduce three popular classification techniques, HMM, SVM, ANN and Non-Negative Matrix Deconvolution (NMD) for SED. The main purpose of this paper is to compare the performance of (1) HMM, (2) hybrid SVM/NMD (3) hybrid SVM/HMM and (4) hybrid MLP /HMM approaches to SED and emphasize approaches to reaching lower Event Error Rates (EER). It was found that the hybrid SVM/HMM approach outperformed the HMM system. Regarding EER, an improvement of 6% was achieved. The hybrid MLP/HMM got the best EER rate. Improvements of 11% and 8% were found in comparison with the HMM and hybrid SVM/HMM event detector, respectively.

Mitochondrial Dysfunction in Huntington’s Disease

Mitochondrial dysfunction has been described as an early pathological mechanism delineating the selective neurodegeneration that occurs in Huntingtons disease (HD), a polyglutamine-expansion disorder that largely affects the striatum and the cerebral cortex. Over the years, mitochondria roles in eukaryotic cells (e.g. in neurons) have largely diverged from the classically attributed cell power source; indeed, mitochondria not only contribute for synthesis of several metabolites, but are also dynamic organelles that fragment and fuse to achieve a maximal bioenergetic performance, are transported along microtubules, regulate intracellular calcium homeostasis through the interaction with the endoplasmic reticulum, produce free radicals and participate in cell death processes. Indeed, most of these activities have been demonstrated to be affected in HD, potentially contributing for the neuronal dysfunction in pre-symptomatic stages. This chapter resumes some of the evidences that pose mitochondria as a main regulatory organelle in HD-affected neurons, uncovering some potentially therapeutic mitochondrial-based relevant targets.

Automatic Annotation of Disfluent Speech in Children’s Reading Tasks

The automatic evaluation of reading performance of children is an important alternative to any manual or 1-on-1 evaluation by teachers or tutors. To do this, it is necessary to detect several types of reading miscues. This work presents an approach to annotate reading speech while detecting false-starts, repetitions and mispronunciations, three of the most common disfluencies. Using speech data of 6–10 year old children reading sentences and pseudowords, we apply a two-step process: first, an automatic alignment is performed to get the best possible word-level segmentation and detect syllable based false-starts and word repetitions by using a strict FST (Finite State Transducer); then, words are classified as being mispronounced or not through a likelihood measure of pronunciation by using phone posterior probabilities estimated by a neural network. This work advances towards getting the amount and severity of disfluencies to provide a reading ability score computed from several sentence reading tasks.

Broad phonetic class definition driven by phone confusions

Intermediate representations between the speech signal and phones may be used to improve discrimination among phones that are often confused. These representations are usually found according to broad phonetic classes, which are defined by a phonetician. This article proposes an alternative data-driven method to generate these classes. Phone confusion information from the analysis of the output of a phone recognition system is used to find clusters at high risk of mutual confusion. A metric is defined to compute the distance between phones. The results, using TIMIT data, show that the proposed confusion-driven phone clustering method is an attractive alternative to the approaches based on human knowledge. A hierarchical classification structure to improve phone recognition is also proposed using a discriminative weight training method. Experiments show improvements in phone recognition on the TIMIT database compared to a baseline system.