A Food Recognition System for Diabetic Patients based on an Optimized Bag of Features Model

Computer vision-based food recognition could be used to estimate a meal's carbohydrate content for diabetic patients. This study proposes a methodology for automatic food recognition, based on the Bag of Features (BoF) model. An extensive technical investigation was conducted for the identification and optimization of the best performing components involved in the BoF architecture, as well as the estimation of the corresponding parameters. For the design and evaluation of the prototype system, a visual dataset with nearly 5,000 food images was created and organized into 11 classes. The optimized system computes dense local features, using the scale-invariant feature transform on the HSV color space, builds a visual dictionary of 10,000 visual words by using the hierarchical k-means clustering and finally classifies the food images with a linear support vector machine classifier. The system achieved classification accuracy of the order of 78%, thus proving the feasibility of the proposed approach in a very challenging image dataset.

Speech Intelligibility in Noise With a Pinna Effect Imitating Cochlear Implant Processor.

OBJECTIVE To evaluate the speech intelligibility in noise with a new cochlear implant (CI) processor that uses a pinna effect imitating directional microphone system. STUDY DESIGN Prospective experimental study. SETTING Tertiary referral center. PATIENTS Ten experienced, unilateral CI recipients with bilateral severe-to-profound hearing loss. INTERVENTION All participants performed speech in noise tests with the Opus 2 processor (omnidirectional microphone mode only) and the newer Sonnet processor (omnidirectional and directional microphone mode). MAIN OUTCOME MEASURE The speech reception threshold (SRT) in noise was measured in four spatial settings. The test sentences were always presented from the front. The noise was arriving either from the front (S0N0), the ipsilateral side of the CI (S0NIL), the contralateral side of the CI (S0NCL), or the back (S0N180). RESULTS The directional mode improved the SRTs by 3.6 dB (p < 0.01), 2.2 dB (p < 0.01), and 1.3 dB (p < 0.05) in the S0N180, S0NIL, and S0NCL situations, when compared with the Sonnet in the omnidirectional mode. There was no statistically significant difference in the S0N0 situation. No differences between the Opus 2 and the Sonnet in the omnidirectional mode were observed. CONCLUSION Speech intelligibility with the Sonnet system was statistically different to speech recognition with the Opus 2 system suggesting that CI users might profit from the pinna effect imitating directionality mode in noisy environments.

Adapting a speech into sign language translation system to a new domain

This paper presents a methodology for adapting an advanced communication system for deaf people in a new domain. This methodology is a user-centered design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. In this paper, the new considered domain has been the dialogues in a hotel reception. With this methodology, it was possible to develop the system in a few months, obtaining very good performance: good speech recognition and translation rates (around 90%) with small processing times.

Non uniform embedding based on relevance analysis with reduced computational complexity: application to the detection of pathologies from biosignal recordings

Nonlinear analysis tools for studying and characterizing the dynamics of physiological signals have gained popularity, mainly because tracking sudden alterations of the inherent complexity of biological processes might be an indicator of altered physiological states. Typically, in order to perform an analysis with such tools, the physiological variables that describe the biological process under study are used to reconstruct the underlying dynamics of the biological processes. For that goal, a procedure called time-delay or uniform embedding is usually employed. Nonetheless, there is evidence of its inability for dealing with non-stationary signals, as those recorded from many physiological processes. To handle with such a drawback, this paper evaluates the utility of non-conventional time series reconstruction procedures based on non uniform embedding, applying them to automatic pattern recognition tasks. The paper compares a state of the art non uniform approach with a novel scheme which fuses embedding and feature selection at once, searching for better reconstructions of the dynamics of the system. Moreover, results are also compared with two classic uniform embedding techniques. Thus, the goal is comparing uniform and non uniform reconstruction techniques, including the one proposed in this work, for pattern recognition in biomedical signal processing tasks. Once the state space is reconstructed, the scheme followed characterizes with three classic nonlinear dynamic features (Largest Lyapunov Exponent, Correlation Dimension and Recurrence Period Density Entropy), while classification is carried out by means of a simple k-nn classifier. In order to test its generalization capabilities, the approach was tested with three different physiological databases (Speech Pathologies, Epilepsy and Heart Murmurs). In terms of the accuracy obtained to automatically detect the presence of pathologies, and for the three types of biosignals analyzed, the non uniform techniques used in this work lightly outperformed the results obtained using the uniform methods, suggesting their usefulness to characterize non-stationary biomedical signals in pattern recognition applications. On the other hand, in view of the results obtained and its low computational load, the proposed technique suggests its applicability for the applications under study.

GTH-UPM system for search on speech evaluation

This paper describes the GTH-UPM system for the Albayzin 2014 Search on Speech Evaluation. Teh evaluation task consists of searching a list of terms/queries in audio files. The GTH-UPM system we are presenting is based on a LVCSR (Large Vocabulary Continuous Speech Recognition) system. We have used MAVIR corpus and the Spanish partition of the EPPS (European Parliament Plenary Sessions) database for training both acoustic and language models. The main effort has been focused on lexicon preparation and text selection for the language model construction. The system makes use of different lexicon and language models depending on the task that is performed. For the best configuration of the system on the development set, we have obtained a FOM of 75.27 for the deyword spotting task.

Human activity recognition by inertial signals obtained from a smartphone

Human Activity Recognition (HAR) is an emerging research field with the aim to identify the actions carried out by a person given a set of observations and the surrounding environment. The wide growth in this research field inside the scientific community is mainly explained by the high number of applications that are arising in the last years. A great part of the most promising applications are related to the healthcare field, where it is possible to track the mobility of patients with motor dysfunction as also the physical activity in patients with cardiovascular risk. Until a few years ago, by using distinct kind of sensors, a patient follow-up was possible. However, far from being a long-term solution and with the smartphone irruption, that monitoring can be achieved in a non-invasive way by using the embedded smartphone’s sensors. For these reasons this Final Degree Project arises with the main target to evaluate new feature extraction techniques in order to carry out an activity and user recognition, and also an activity segmentation. The recognition is done thanks to the inertial signals integration obtained by two widespread sensors in the greater part of smartphones: accelerometer and gyroscope. In particular, six different activities are evaluated walking, walking-upstairs, walking-downstairs, sitting, standing and lying. Furthermore, a segmentation task is carried out taking into account the activities performed by thirty users. This can be done by using Hidden Markov Models and also a set of tools tested satisfactory in speech recognition: HTK (Hidden Markov Model Toolkit).

Computer speech synthesis: its status and prospects.

Computer speech synthesis has reached a high level of performance, with increasingly sophisticated models of linguistic structure, low error rates in text analysis, and high intelligibility in synthesis from phonemic input. Mass market applications are beginning to appear. However, the results are still not good enough for the ubiquitous application that such technology will eventually have. A number of alternative directions of current research aim at the ultimate goal of fully natural synthetic speech. One especially promising trend is the systematic optimization of large synthesis systems with respect to formal criteria of evaluation. Speech recognition has progressed rapidly in the past decade through such approaches, and it seems likely that their application in synthesis will produce similar improvements.

Integration of speech with natural language understanding.

The integration of speech recognition with natural language understanding raises issues of how to adapt natural language processing to the characteristics of spoken language; how to cope with errorful recognition output, including the use of natural language information to reduce recognition errors; and how to use information from the speech signal, beyond just the sequence of words, as an aid to understanding. This paper reviews current research addressing these questions in the Spoken Language Program sponsored by the Advanced Research Projects Agency (ARPA). I begin by reviewing some of the ways that spontaneous spoken language differs from standard written language and discuss methods of coping with the difficulties of spontaneous speech. I then look at how systems cope with errors in speech recognition and at attempts to use natural language information to reduce recognition errors. Finally, I discuss how prosodic information in the speech signal might be used to improve understanding.

Speech technology in 2001: new research directions.

Research in speech recognition and synthesis over the past several decades has brought speech technology to a point where it is being used in "real-world" applications. However, despite the progress, the perception remains that the current technology is not flexible enough to allow easy voice communication with machines. The focus of speech research is now on producing systems that are accurate and robust but that do not impose unnecessary constraints on the user. This chapter takes a critical look at the shortcomings of the current speech recognition and synthesis algorithms, discusses the technical challenges facing research, and examines the new directions that research in speech recognition and synthesis must take in order to form the basis of new solutions suitable for supporting a wide range of applications.

A corpus-based analysis of transfer effects and connected speech processes in Vietnamese English

This paper presents a corpus-based descriptive analysis of the most prevalent transfer effects and connected speech processes observed in a comparison of 11 Vietnamese English speakers (6 females, 5 males) and 12 Australian English speakers (6 males, 6 females) over 24 grammatical paraphrase items. The phonetic processes are segmentally labelled in terms of IPA diacritic features using the EMU speech database system with the aim of labelling departures from native-speaker pronunciation. An analysis of prosodic features was made using ToBI framework. The results show many phonetic and prosodic processes which make non-native speakers’ speech distinct from native ones. The corpusbased methodology of analysing foreign accent may have implications for the evaluation of non-native accent, accented speech recognition and computer assisted pronunciation- learning.

A comparative evaluation of term recognition algorithms

Automatic Term Recognition (ATR) is a fundamental processing step preceding more complex tasks such as semantic search and ontology learning. From a large number of methodologies available in the literature only a few are able to handle both single and multi-word terms. In this paper we present a comparison of five such algorithms and propose a combined approach using a voting mechanism. We evaluated the six approaches using two different corpora and show how the voting algorithm performs best on one corpus (a collection of texts from Wikipedia) and less well using the Genia corpus (a standard life science corpus). This indicates that choice and design of corpus has a major impact on the evaluation of term recognition algorithms. Our experiments also showed that single-word terms can be equally important and occupy a fairly large proportion in certain domains. As a result, algorithms that ignore single-word terms may cause problems to tasks built on top of ATR. Effective ATR systems also need to take into account both the unstructured text and the structured aspects and this means information extraction techniques need to be integrated into the term recognition process.

Evaluating the appropriateness of speech input in marine applications : a field evaluation

This paper discusses the first of three studies which collectively represent a convergence of two ongoing research agendas: (1) the empirically-based comparison of the effects of evaluation environment on mobile usability evaluation results; and (2) the effect of environment - in this case lobster fishing boats - on achievable speech-recognition accuracy. We describe, in detail, our study and outline our results to date based on preliminary analysis. Broadly speaking, the potential for effective use of speech for data collection and vessel control looks very promising - surprisingly so! We outline our ongoing analysis and further work.

Evaluating the appropriateness of speech input in marine applications:a field evaluation

This paper discusses the first of three studies which collectively represent a convergence of two ongoing research agendas: (1) the empirically-based comparison of the effects of evaluation environment on mobile usability evaluation results; and (2) the effect of environment - in this case lobster fishing boats - on achievable speech-recognition accuracy. We describe, in detail, our study and outline our results to date based on preliminary analysis. Broadly speaking, the potential for effective use of speech for data collection and vessel control looks very promising - surprisingly so! We outline our ongoing analysis and further work.

The resolution of complex spectral patterns by cochlear implant and normal-hearing listeners

The differences in spectral shape resolution abilities among cochlear implant ~CI! listeners, and between CI and normal-hearing ~NH! listeners, when listening with the same number of channels ~12!, was investigated. In addition, the effect of the number of channels on spectral shape resolution was examined. The stimuli were rippled noise signals with various ripple frequency-spacings. An adaptive 4IFC procedure was used to determine the threshold for resolvable ripple spacing, which was the spacing at which an interchange in peak and valley positions could be discriminated. The results showed poorer spectral shape resolution in CI compared to NH listeners ~average thresholds of approximately 3000 and 400 Hz, respectively!, and wide variability among CI listeners ~range of approximately 800 to 8000 Hz!. There was a significant relationship between spectral shape resolution and vowel recognition. The spectral shape resolution thresholds of NH listeners increased as the number of channels increased from 1 to 16, while the CI listeners showed a performance plateau at 4–6 channels, which is consistent with previous results using speech recognition measures. These results indicate that this test may provide a measure of CI performance which is time efficient and non-linguistic, and therefore, if verified, may provide a useful contribution to the prediction of speech perception in adults and children who use CIs.

Assessment of two central auditory tests in elderly patients without hearing complaints

Speech understanding disorders in the elderly may be due to peripheral or central auditory dysfunctions. Asymmetry of results in dichotic testing increases with age, and may reflect on a lack of inter-hemisphere transmission and cognitive decline. Aim: To investigate auditory processing of aged people with no hearing complaints. Study design: clinical prospective. Materials and Methods: Twenty-two voluntary individuals, aged between 55 and 75 years, were evaluated. They reported no hearing complaints and had maximal auditory thresholds of 40 dB HL until 4 KHz, 80% of minimal speech recognition scores and peripheral symmetry between the ears. We used two kinds of tests: speech in noise and dichotic alternated dissyllables (SSW). Results were compared between males and females, right and left ears and between age groups. Results: There were no significant differences between genders, in both tests. Their Left ears showed worse results, in the competitive condition of SSW. Individuals aged 65 or older had poorer performances than those aged 55 to 64. Conclusion: Central auditory tests showed worse performance with aging. The employment of a dichotic test in the auditory evaluation setting in the elderly may help in the early identification of degenerative processes, which are common among these patients.