Speech Recognition with Limited Resources for Children and Adult Speakers

2011 ◽  
Author(s):  
Edith Moya ◽  
Manuel Hernandez ◽  
Luis Pineda ◽  
Ivan Meza
Keyword(s):  
Speech Recognition ◽  
Limited Resources

Queec: QoE-aware Edge Computing for IoT Devices under Dynamic Workloads

2021 ◽  
Vol 17 (3) ◽  
pp. 1-23
Author(s):  
Borui Li ◽  
Wei Dong ◽  
Gaoyang Guan ◽  
Jiadong Zhang ◽  
Tao Gu ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Optimization Problem ◽  
State Of The Art ◽  
Computing System ◽  
Edge Computing ◽  
Limited Resources ◽  
Event Processing ◽  
Iot Applications ◽  
Iot Devices ◽  
User Tasks

Many IoT applications have the requirements of conducting complex IoT events processing (e.g., speech recognition) that are hardly supported by low-end IoT devices due to limited resources. Most existing approaches enable complex IoT event processing on low-end IoT devices by statically allocating tasks to the edge or the cloud. In this article, we present Queec, a QoE-aware edge computing system for complex IoT event processing under dynamic workloads. With Queec, the complex IoT event processing tasks that are relatively computation-intensive for low-end IoT devices can be transparently offloaded to nearby edge nodes at runtime. We formulate the problem of scheduling multi-user tasks to multiple edge nodes as an optimization problem, which minimizes the overall offloading latency of all tasks while avoiding the overloading problem. We implement Queec on low-end IoT devices, edge nodes, and the cloud. We conduct extensive evaluations, and the results show that Queec reduces 56.98% of the offloading latency on average compared with the state-of-the-art under dynamic workloads, while incurring acceptable overhead.

scholarly journals Speech Recognition and Speech Synthesis Models for Micro Devices

2019 ◽  
Vol 27 ◽  
pp. 05001
Author(s):  
Bismark Asiedu Asante ◽  
Hiroki Imamura
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Speech Synthesis ◽  
Electronic Devices ◽  
Network Models ◽  
Limited Resources ◽  
Raspberry Pi ◽  
Application Development ◽  
Neural Network Models ◽  
Internet Connectivity

With the advent and breakthrough of interaction between humans and electronic devices using speech in communication, we have seen a lot of applications using speech recognition and speech synthesis technology. There are some limitations we have identified to these applications. Availability of a lot of resources and internet connectivity have made it possible in making case but with limited resources it is quite difficult to achieve this feat. As a result, it limits the application of the technology into micro devices and deploying them into areas where there are no internet connectivity. In this article, we developed a smaller Deep Neural Network models for Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) for communication on micro devices such as Raspberry Pi. We tested and evaluated the models of the system. The accuracy and the performance of the models to be implemented on micro devices shows that they are good for application development in micro devices.

Practical Resources for Provision of Services to Culturally and Linguistically Diverse Users of AAC

2015 ◽  
Vol 22 (1) ◽  
pp. 25-39
Author(s):  
Elena Dukhovny ◽  
E. Betsy Kelly
Keyword(s):  
Best Practices ◽  
Augmentative And Alternative Communication ◽  
Linguistically Diverse ◽  
Intervention Strategies ◽  
Culturally And Linguistically Diverse ◽  
Limited Resources ◽  
Flexible Systems ◽  
Alternative Communication ◽  
Practical Applications ◽  
Provision Of Services

According to the 2010 U.S. Census, over 20% of Americans speak a language other than English in the home, with Spanish, Chinese, and French being the languages most commonly spoken, aside from English. However, few augmentative and alternative communication (AAC) systems offer multilingual support for individuals with limited functional speech. There has been much discussion in the AAC community about best practices in AAC system design and intervention strategies, but limited resources exist to help us provide robust, flexible systems for users who speak languages other than English. We must provide services that take into consideration the unique needs of culturally and linguistically diverse users of AAC and help them reach their full communication potential. This article outlines basic guidelines for best practices in AAC design and selection, and presents practical applications of these best practices to multilingual/multicultural clients.

Selecting the Optimal FM System for Children With Cochlear Implants

2008 ◽  
Vol 18 (1) ◽  
pp. 19-24
Author(s):  
Erin C. Schafer
Keyword(s):  
Speech Recognition ◽  
Cochlear Implants ◽  
Empirical Research ◽  
Background Noise ◽  
Signal To Noise Ratio ◽  
Evidence Based ◽  
Signal To Noise ◽  
Speech Processor ◽  
System Input ◽  
Optimal Type

Children who use cochlear implants experience significant difficulty hearing speech in the presence of background noise, such as in the classroom. To address these difficulties, audiologists often recommend frequency-modulated (FM) systems for children with cochlear implants. The purpose of this article is to examine current empirical research in the area of FM systems and cochlear implants. Discussion topics will include selecting the optimal type of FM receiver, benefits of binaural FM-system input, importance of DAI receiver-gain settings, and effects of speech-processor programming on speech recognition. FM systems significantly improve the signal-to-noise ratio at the child's ear through the use of three types of FM receivers: mounted speakers, desktop speakers, or direct-audio input (DAI). This discussion will aid audiologists in making evidence-based recommendations for children using cochlear implants and FM systems.

Unknown and Under-Researched: The Anatomy of Drinking Under Control Programs

2017 ◽  
Vol 63 (5) ◽  
pp. 277-288
Author(s):  
Harald Klingemann ◽  
Justyna Klingemann
Keyword(s):  
Quality Of Life ◽  
Harm Reduction ◽  
Evaluation Studies ◽  
Mission Statements ◽  
Community Response ◽  
Limited Resources ◽  
Admission Criteria ◽  
Control Programs ◽  
Institutional Order

Abstract. Introduction: While alcohol treatment predominantly focuses on abstinence, drug treatment objectives include a variety of outcomes related to consumption and quality of life. Consequently harm reduction programs tackling psychoactive substances are well documented and accepted by practitioners, whereas harm reduction programs tackling alcohol are under-researched and met with resistance. Method: The paper is mainly based on key-person interviews with eight program providers conducted in Switzerland in 2009 and up-dated in 2015, and the analysis of reports and mission statements to establish an inventory and description of drinking under control programs (DUCPs). A recent twin program in Amsterdam and Essen was included to exemplify conditions impeding their implementation. Firstly, a typology based on the type of alcohol management, the provided support and admission criteria is developed, complemented by a detailed description of their functioning in practice. Secondly, the case studies are analyzed in terms of factors promoting and impeding the implementation of DUCPs and efforts of legitimize them and assess their success. Results: Residential and non-residential DUCPs show high diversity and pursue individualized approaches as the detailed case descriptions exemplify. Different modalities of proactively providing and including alcohol consumption are conceptualized in a wider framework of program objectives, including among others, quality of life and harm reduction. Typically DUCPs represent an effort to achieve public or institutional order. Their implementation and success are contingent upon their location, media response, type of alcohol management and the response of other substance-oriented stake holders in the treatment system. The legitimization of DUCPs is hampered by the lack of evaluation studies. DUCPs rely mostly – also because of limited resources – on rudimentary self-evaluations and attribute little importance to data collection exercises. Conclusions: Challenges for participants are underestimated and standard evaluation methodologies tend to be incompatible with the rationale and operational objectives of DUCPs. Program-sensitive multimethod approaches enabled by sufficient financing for monitoring and accompanying research is needed to improve the practice-oriented implementation of DUCPs. Barriers for these programs include assumptions that ‘alcohol-assisted’ help abandons hope for recovery and community response to DUCPs as locally unwanted institutions (‘not in my backyard’) fuelled by stigmatization.

A Typology of Caregiving Situations and Service Use in Family Carers of Older People in Six European Countries

GeroPsych ◽  
2011 ◽  
Vol 24 (1) ◽  
pp. 5-18 ◽  
Author(s):  
Mirko Di Rosa ◽  
Christopher Kofahl ◽  
Kevin McKee ◽  
Barbara Bień ◽  
Giovanni Lamura ◽  
...  
Keyword(s):  
Health Services ◽  
Older People ◽  
Support Services ◽  
Family Caregiving ◽  
Service Use ◽  
European Countries ◽  
Limited Resources ◽  
Family Carers ◽  
Policy Initiatives ◽  
Typology Of Care

This paper presents the EUROFAMCARE study findings, examining a typology of care situations for family carers of older people, and the interplay of carers with social and health services. Despite the complexity of family caregiving situations across Europe, our analyses determined the existence of seven “caregiving situations,” varying on a range of critical indicators. Our study also describes the availability and use of different support services for carers and care receivers, and carers’ preferences for the characteristics of support services. Our findings have relevance for policy initiatives in Europe, where limited resources need to be more equitably distributed and services should be targeted to caregiving situations reflecting the greatest need, and organized to reflect the preferences of family carers.

Sign in / Sign up

Export Citation Format

Share Document