Automatic Speech Classifier for Mild Cognitive Impairment and Early Dementia

The World Health Organization estimates that 50 million people are currently living with dementia worldwide and this figure will almost triple by 2050. Current pharmacological treatments are only symptomatic, and drugs or other therapies are ineffective in slowing down or curing the neurodegenerative process at the basis of dementia. Therefore, early detection of cognitive decline is of the utmost importance to respond significantly and deliver preventive interventions. Recently, the researchers showed that speech alterations might be one of the earliest signs of cognitive defect, observable well in advance before other cognitive deficits become manifest. In this article, we propose a full automated method able to classify the audio file of the subjects according to the progress level of the pathology. In particular, we trained a specific type of artificial neural network, called autoencoder, using the visual representation of the audio signal of the subjects, that is, the spectrogram. Moreover, we used a data augmentation approach to overcome the problem of the large amount of annotated data usually required during the training phase, which represents one of the most major obstacles in deep learning. We evaluated the proposed method using a dataset of 288 audio files from 96 subjects: 48 healthy controls and 48 cognitively impaired participants. The proposed method obtained good classification results compared to the state-of-the-art neuropsychological screening tests and, with an accuracy of 90.57%, outperformed the methods based on manual transcription and annotation of speech.

Software for Creating Self-Made Content With Multimedia-Enabled Dot Codes and Gifted School Activities for Students With Disabilities

Gifted school activities for students with various disabilities were presented with self-made original content created with newly-developed software—Sound Linker, File Linker, GM Authoring Tool, and Gridmark Content Viewer software—that can handle multimedia-enabled dot codes, originally developed by Gridmark, Inc. Each dot codes can link up to four multimedia mediums—such as a movie—in addition to up to four voices/sounds. Touching dot codes with a speaking-pen enables audio files to be replayed, and touching dot codes with a dot-code reader enables multimedia to be replayed on iOS and Windows OS devices. Software and Post-it® sticker icon overlaid with dot codes and a speaking-pen and dot-code reader are distributed for free to school teachers. All the teachers can now create their own self-made original content and can conduct related school activities without buying any costly software and tools. Basic information on (1) creating original teaching materials using the developed software and (2) its use in schools for students with various difficulties is presented in this chapter.

Introducing Language and Society

This accessible and entertaining textbook introduces students to both traditional and more contemporary approaches to sociolinguistics in a real-world context, addressing current social problems that students are likely to care about, such as racism, inequality, political conflict, belonging, and issues around gender and sexuality. Each chapter includes exercises, case studies and ideas for small-scale research projects, encouraging students to think critically about the different theories and approaches to language and society, and to interrogate their own beliefs about language and communication. The book gives students a grounding in the traditional concepts and techniques upon which sociolinguistics is built, while also introducing new developments from the last decade, such as translanguaging, multimodality, superdiversity, linguistic landscapes and language and digital media. Students will also have online access to more detailed examples, links to video and audio files, and more challenging exercises to strengthen their skills and confidence as sociolinguists.

LSB-based Audio Steganographical Framework for Securing Data in Transit

The benefits that individuals and organizations derive from the digital era comes with its own challenges. Globally, data has become one of the greatest assets for decision making and operational improvements among businesses, government agencies and even individuals. Data on its own and at its source does not make so much contribution to business processes. Data is transmitted from one location to another towards attainment of its goal as a critical resource in decision making. However, data including sensitive or confidential ones are transmitted via public channels such as the Internet. The data so transmitted via the Internet is vulnerable to interception and unauthorized manipulation. This demands that data in transit is protected from the prying eyes of the malicious internet users. One of such strategies for transmitting data via public channels such as the Internet without attracting attention from intruders is steganography. In this paper, the least significant bit algorithm was used with an audio file for hiding data in transit. The algorithm used in this research proves to be one of the simplest ways of securing data using audio steganography. The method employed the LSB technique by using audio files as the stego object for the final implementation in the Java programming language. The experimental results proved to be one of the best methods of implementing steganography. The accuracy of the stego objects shows high quality, and similarity scores with an improved processing time.

SCORING THE JOURNEY: LISTENING TO CLAUDIA MOLITOR'S SONORAMA

Sonorama is a 2015 sonic artwork by Claudia Molitor, consisting of a number of audio files designed for listening on a train journey between London St Pancras and Margate, and a graphic score based on the composer's own ‘reading’ of this journey. This article analyses the relationship between the sonic and the spatial in the work, exploring how Molitor's site-specific composition interacts with its environment on multiple scales. By drawing on the strategy of ‘situated listening’ developed by Gascia Ouzounian, as well as urbanist language introduced by Richard Sennett, this article seeks to elucidate the relationship between a number of ‘nested’ spaces, present across varying realisations, and the political agenda that energises the work. Written in the midst of summer 2015's European refugee crisis, the work brings into sharp focus themes of British exceptionalism, immigration and inclusion.

LSBR Speech Steganalysis Based on Percent of Equal Adjacent Samples

Wide utilization of audio files has attracted the attention of cyber-criminals to employ this media as a cover for their concealed communications. As a countermeasure and to protect cyberspace, several techniques have been introduced for steganalysis of various audio formats, such as MP3, VoIP, etc. The combination of machine learning and signal processing techniques has helped steganalyzers to obtain higher accuracies. However, as the statistical characteristics of a normal audio file differ from the speech ones, the current methods cannot discriminate clean and stego speech instances efficiently. Another problem is the high numbers of extracted features and analysis dimensions that drastically increase the implementation cost. To tackle these, this paper proposes the Percent of Equal Adjacent Samples (PEAS) feature for single-dimension least-significant-bit replacement (LSBR) speech steganalysis. The model first classifies the samples into speech and silence groups according to a threshold which has been determined through extensive experiments. It then uses an MLP classifier to detect stego instances and determine the embedding ratio. PEAS steganalysis detects 99.8% of stego instances in the lowest analyzed embedding ratio — 12.5% — and its sensitivity increases to 100% for the ratios of 37.5% and above.

Taking a deep breath

While 2012 is going away, IJHDR prepares the celebration of its 5th anniversary! This is thus a time for reflection, to ponder on the good and bad experiences, to (re)think the next steps to improve our service to readers, authors and the scientific community at large. Along these hard, but rewarding first five years, IJHDR reached many readers and was supported by many authors all over the world, it achieved recognition by important scientific databases and societies. This success is the result of the joint work of the Editorial Board members and with GIRI, our hosting scientific society. IJHDR provided the homeopathic community an open, free, multimedia and electronic venue to share high-quality information. Focused on research articles, and open to the entire field of High Dilution research, including homeopathy and hormesis, IJHDR came to occupy a special place within the scientific map. Nevertheless, the goals achieved are not enough, but further improvement is needed for IJHDR keep on growing. Our aim for the next years is to maintain the original editorial vision and mission, while increasing even more the quality of publication. IJHDR will start 2013 by revising its Board of Consultants. Five years ago, when IJHDR was an unknown journal that still had to prove its quality, friends, idealists, and invited experts kindly contributed with their expertise to make peer review a mandatory step in the evaluation of articles. However, not only IJHDR grew, but also the editorial work did! The time arrives to include new experts in our Board of Consultant,, not only to share in the work, but to have cover a broader scope of knowledge, as HD research is a cross-disciplinary and emergent field. Also the structure of the articles will be revised. Improvement in the layout will be discussed to stimulate the use of multimedia resources like video and audio files, simulations, supplementary materials, links, and color images. Special attention will be paid to language revision and reference citation. Together with its authors and readers, IJHDR contributes to the development of a kind of knowledge close to the borders of science. Therefore, to establish a valid scientific background, the articles must be clearly written, and based on sound assumptions. High-visibility for articles is a fundamental aspect desired by all authors. As an open and free access journal, IJHDR meets that condition, and we are planning to make our influence and visibility even wider. Inclusion in the major databases has paramount importance in the academic milieu, however, it should be considered as a consequence, rather than a goal. In 2013, IJHDR will chair a collaborative project with several research institutions aiming to deliver information everywhere, increasing the visibility of the published articles. Thus, now it is the time to take a deep breath, relax, and prepare you for the forthcoming work! See you in 2013!

Quantum Proof Encryption Technology

Nowadays we use text passwords to encrypt a file. This research paper proposes to use multimedia files like images videos, audio files and even applications as the password key to encrypt sensitive information. This algorithm can encrypt bulk data as well as single data sets. Keywords: steganography, multimedia file as key, Quantum computer, cryptography, Quantum computer proof encryption.

Unilateral Vocal Fold Paralysis: The “Trifecta”—Dysphonia, Dysphagia, and Dyspnea

Purpose: A clinical case of unilateral vocal fold paralysis is presented with case history, auditory-perceptual analysis and accompanying audio files and ratings, videostroboscopic files and ratings, and acoustic analysis, as well as impressions and plan for treatment. Method: A single clinical case of unilateral vocal fold paralysis is presented for learning purposes. Results: Clinical keys are provided for learning. Conclusion: Learners will be able to follow a clinical case to aid in perceptual, videostroboscopic, acoustic, and voice assessment and goal and treatment planning. Supplemental Material https://doi.org/10.23641/asha.16799563

Internet-based language production research with overt articulation: Proof of concept, challenges, and practical advice

Language production experiments with overt articulation have thus far only scarcely been conducted online, mostly due to technical difficulties related to measuring voice onset latencies. Especially the poor audiovisual synchrony in web experiments (Bridges et al. 2020) is a challenge to time-locking stimuli and participants’ spoken responses. We tested the viability of conducting language production experiments with overt articulation in online settings using the picture–word interference paradigm – a classic task in language production research. In three pre-registered experiments (N = 48 each), participants named object pictures while ignoring visually superimposed distractor words. We implemented a custom voice recording option in two different web experiment builders and recorded naming responses in audio files. From these stimulus-locked audio files, we extracted voice onset latencies offline. In a control task, participants classified the last letter of a picture name as a vowel or consonant via button-press, a task that shows comparable semantic interference effects. We expected slower responses when picture and distractor word were semantically related compared to unrelated, independently of task. This semantic interference effect is robust, but relatively small. It should therefore crucially depend on precise timing. We replicated this effect in an online setting, both for button-press and overt naming responses, providing a proof of concept that naming latency – a key dependent variable in language production research – can be reliably measured in online experiments. We discuss challenges for online language production research and suggestions of how to overcome them. The scripts for the online implementation are made available.