Proposed Solution for Seamus Corporation

Seamus Corporation targets at designing, developing and implementing a technological solution that integrates emerging knowledge in the teaching, text mechanics, articulation of words and other related concepts in English. SC is recommended to execute an application which will incorporate current English concepts offered by the company in books and a speech-to-text software. Execution of the proposed system is expected to increase the overall performance of students in middle and high school level. The planned project will also apply to teaching people with disabilities.  The primary goals of the project are to implement voice recognition technology in schools and to improve student’s performance in the English language. The program will take approximately 31 days to be completed entirely and it will cost $ 20,545. The submitting organization has experts in information technology who are capable of assimilating a speech-to-text software and the English curriculum SC offers into one application.   

A proposed project for Seamus Company

D1. Proposed Solution

Seamus Company manages products development and operations internally.  As a result of a wide range of opportunities requiring optimization and commodities needing innovative enhancements within the scope of the company, SC seeks an expert with abilities associated with the operations. The professional is required to enhance the products or invent new commodities which will be marketed and sold by SC portfolio. The company pursues to develop, establish and execute technology resolutions which assimilate new and emerging knowledge in the tutoring of English grammar, general articulation, writing mechanism or associated concepts.  An appropriate solution to these problems includes the use of Speech-to-text technology. In the contemporary society, there is a growing need to shift from paperwork to application of the electronic method of teaching and learning. A speech-to-text technology is capable of integrating the existing and emerging knowledge in the instruction, text mechanics, pronunciation and other associated topics in the English language.    

A speech-to-text technology solution will help in an efficient implementation of the video game which was created by SC after contracting TechFite firm. By introduction of a speech-to-text technology, SC firm will shift from the printing of English books and related volumes to use of mobile-based and computer-centered applications. The proposed speech-to-text technologies can be used to assist in writing improvement for English language learners across all ages, from children to adults. These notions will be used to help English writing progression for any content area or aim. Speech-to-text technology is also referred to as speech recognition due to its ability to identify the voice. The technology allows the speech to act as the primary interface between the computer and the person. Speech-to-text technology will accelerate learning of students with various disabilities. The current use of books and video games does not cater for students with disabilities.

For students with physical inabilities, low vision or blindness, and motor skill limitations, hands-free computing via application of speech recognition knowledge will be beneficial. By eliminating the physical obstruction to the navigation of computer and writing, SC Company will increase student access to classroom activities and technology. Speech recognition knowledge will encourage writing which is more deliberate and thoughtful for the pupils with learning disorders. Research has depicted that input through speech is less problematic and that pupils frequently produce papers which are longer and with improved quality by use of the speech-to-text technology (Dodd, 2012).        

D2. Case Study Review

Hsiao et al. (2016) assess the new BBN speech recognition platform. The researchers established a mechanism called sage that tolerates fast exchange of speech-to-text constituents from several sources. To exploit the rapid expansion of voice recognition knowledge and propagation of open source appliance education toolkits, BBN firm has initiated sage, a new voice generating technique which incorporates knowledge from various sources (Hsiao et al., 2016 ). The design of sage aims to offer an interface to integrate technologies from various projects. Sage technology is flexible enough to permit components to be exchanged to reduce the time for prototyping. Further, technology transmission is critical hence sage aims at allowing the investigators to transfer the latest knowledge to applications straightforwardly (Hsiao et al., 2016 ). Through its segmental design and python interface, sage can take advantages of numerous open source toolkits. To depict the effectiveness of sage as a production scheme, the researchers established a high-performance English program and demonstrated that it could operate in real-time with a small quantity of memory consumption.   

Nuance is at the center of the boom in voice expertise. The firm was started in 1992 as Visioneer and has acquired many other voice technology organizations. Recently, Nuance has skillfully used its professionalism in voice recognition to the developing market for speech interfaces. The organization supplies voice recognition knowledge to other firms, and it is believed to offer the speech element of Siri (Khayyat, 2017 ). According to Nuance’s CTO, speech is supremely appropriate to mobile computing since a single spoken command can complete tasks which may require many presses and swipes by use of typing (Khayyat, 2017 ).  Since the voice recognition software on cellphones has succeeded, Nuance now aims at putting speech interfaces in automobiles and televisions. The voice technology is simple and can be applied in any sector including in elementary and high schools.

Adams (2017) conducted an assessment of the efficiency of applying voice recognition knowledge to sustain inscription of pupils with learning disorders. The researcher inspected the impacts of implementing voice-to-text knowledge to establish more cohesion writing for pupils suffering from learning disorders as likened to the pencil and paper. The participants of the study were six pupils with learning disabilities from general education schoolrooms, aged between 7 years to 9 years old (Adams, 2017 ).  Before embarking on the assessment, the respondents completed a baseline investigation aimed at measuring their communicative inscription skills in reaction to a description prompt. The pupils were required to include a subject sentence, start, central part and conclusion as a way of examining their comprehension of the agreements of writing (Adams, 2017 ).  The researcher aimed at looking at the quality of the texts as opposed to the number of words written. The writings were graded to find measurements for holistic quality, grammar, and mechanics of writing, organization, and cohesiveness of English language used. The participants were then submitted to another writing examination by the use of speech-to-text technology (Adams, 2017 ). There were little improvements in writing by the use of speech-to-text knowledge. However, the study identified that further submission of the pupils to the speech-to-text technology would improve their writing skills.       

D3. Goals, Objectives, and Deliverables

1. To fully implement speech-to-text technology in middle and high school education.

a) Create a mobile-based application to accommodate grammar books for middle and high school students.

i) Collaborate with Apple Corporation. The mobile and computer hardware will be sourced from these two companies.

ii) Purchase of speech-to-text software.

iii) Incorporate middle and high school English language curriculum in the software with the help of IT specialists.

2. To improve the instruction of English grammar, text mechanics and general articulation.

a) To include an updated English dictionary in the application. Pronunciation provides by the English dictionary will be fed in the speech-to-text application.

i) Install the application into 4 sample hardware that is in two tablets and two personal computers. 

ii) Tests for the effectiveness of the speech-to-text application.

iii) Examination of the efficiency of the speech-to-text application among the disabled students.

iv) Team up with various schools to train the teachers and encourage the institutions to implement the speech-to-text technology.

v) After the success of the project, the submitting firm will enable updates of the software after a given period. SC will to update the application after sometimes to cater for a change of curriculum and addition of topics.

D4. Projected Timeline

Description of milestone or deliverable

Duration

(hours or days)

Projected start date

Anticipated end date

Collaboration with Apple corporation

14 days

02/04/2018

16/04/2018

Purchase of speech-to-text software.

Three days

17/04/2018

20/04/2018

Incorporate middle and high school English language curriculum in the software with the close assistance of IT experts.

Two days

21/04/2018

23/04/2018

Install the application into 4 sample hardware that is in two tablets and two personal computers. 

12 hours

24/04/2018

24/04/2018

Tests for the effectiveness of the speech-to-text application.

One day

25/04/2018

26/04/2018

Examination of the efficiency of the speech-to-text application among the disabled students.

Two days

27/04/2018

29/04/2018

Team up with various schools to train the teachers and encourage the institutions to implement the speech-to-text technology.

Eight days

30/04/2018

08/06/2018

Table 1: Projected Timeline

D5. Resources and Costs

The primary resource for the proposed project is a voice recognition software. A voice-to-text application cost is determined by its accuracy and speed. The software varies in costs, features, and overall precision. SC requires software which accurately and quickly decodes the words dictated to it by users to text. The software also needs also to be independent of the pronunciation of words in different assent and domestic dialect. However, users should at least pronounce all words as they are expressed in the Oxford dictionary. The software will have the ability to edit and format documents. Currently, a comprehensive voice recognition software provided by Nuance firm costs 1600 USD (Olenewa, 2014 ). Other expenses linked with the application include a microphone device that costs 25 USD, go-live support at 150 USD, one-on-one training by the provider at 300 USD and yearly maintenance price of 320 USD (Olenewa, 2014 ).

The execution of the project needs two tablets and two personal computers. The integrated application consisting of a voice recognition software and the English curriculum for middle and high school level will be installed on these four devices. The four devices will be used in training teachers and administrators of various schools. An average iPad costs $ 686 while mac price is $1499 at Amazon online shopping platform (Olenewa, 2014 ). The devices will be needed back for future use by the SC after the training. Then, there is need to purchase Apple products since they are considered to be durable and reliable.  

Given that SC has the English curriculum in softcopy form, the integration of this syllabus will be less costly. There is a requirement to hire IT, experts, to integrate the curriculum with the voice recognition software. Two experts paid at $50 per hour will assist in integrating these two components together. Then, the total external labor cost will cost SC Company a total of $ 1600 (Weckert et al., 2013 ). Training of the selected school teachers and administrators will be done by eight internal employees of SC firm. These employees will earn an allowance of $200 per day as a measure of increasing their productivity during the training sessions. The allowance cost then totals up to 12,800 USD.

Unit

Quantity

Costs  (USD)

Voice recognition software

1

1,600

Microphone device

1

25

Go-live support

1

150

IPad

2

1,372

Personal computer

2

2,998

IT expert wages (the submitting firm)

2

1,600

Employee training Allowance cost

8

12,800

Total cost

20,545

Table 2: Project Costs

D6. Outcome

Objective

Anticipated result

Measurement

Integration of voice recognition software and English curriculum software.

The voice recognition software and the English subjects are expected to be compatible in an application. The two components are in small magnitudes hence they will be compatible on an iPad and in a personal computer. 100 % readability of incorporated English content is expected

Readability of incorporated English curriculum.

Initiation of the speech-to-text technology in middle and high schools.

English writing and reading performance of students is expected to increase by 50 %.  

-English performance

- An increase in the number of students in schools

Introduction of the integrated voice recognition in schools for the disabled people.

A 20% of English performance increase is expected from students with various disabilities.   

-English performance

- An increase in the number of students in these schools

To recognize words pronounced in different accents.

A 100 % pronunciation improvement is expected from the students. 

Pronunciation accuracy

To increase writing accuracy

An 80 % increase in writing accuracy is expected from the students.

Text accuracy

Table 3: Outcome

E. Justification and Proposal Highlights

According to the request for proposal, SC aims at developing, designing and executing technological remedies which integrate developing knowledge in the tutoring of English grammar, writing mechanism, the overall pronunciation of words and other associated concepts. The nature of the proposed project is to migrate paperwork to fully digital writing and reading. A program will be developed to incorporate a voice recognition software and English syllabus provided currently by SC for middle and high school students. The students will make use of tablets and personal computers to do various school work. The pupils will command the new gadgets to produce a text by use of their voice. Voice recognition technology is an existing knowledge, but it has not been utilized fully in the education system. With the proposed learning gadgets, SC will find a new market where it has not reached currently that is the schools for the disabled. Various individuals and companies have applied or researched on the use of voice recognition technology. The technology of voice recognition has been recognized as an appropriate way to improve writing and effectiveness English language. A total of 31 days is required to complete the proposed project.  The scheme will cost $ 20,545 and numerous benefits are anticipated.  

The project is expected to improve the performance of the students. The program will increase the accuracy of pronunciation by rejecting incorrectly pronounced words. However, the program is anticipated to accept words pronounce in different language accents. If a pupil has little or no writing skills, voice recognition can assist such individual to switch from incapability to capability since the applications assist in viewing the spoken English language in print form. When a pupil struggles over apprehension, use of voice recognition is an appropriate remedy. As time goes by, the anxiety will reduce, and the student will build enough self-reliance and independence. The speech-to-text application is an effective tool for students who struggle in pronouncing English words. The proposed voice recognition software is useful for students who struggle with their cognitive, academic, language and proficiency. Further, the projected program will apply to people with various inabilities since only a voice in needed to produce texts.    

SC aims at catching up with emerging technologies in the production of books and writing materials. As IT firm, the submitting firm is an appropriate bidder for SC proposal. The firm consists of individuals with skills in IT. The information technology skills will be of great assistance in incorporating the voice recognition software and the current English curriculum in a single application. The new product will create an opportunity for SC to trade its English learning materials to schools for the students with disabilities. Seamus Company should commit itself to funding this project since it is profitable. The integrated voice recognition application is expected to increase the performance of students in English. As a result, the program will be accepted in numerous schools thus creating a broad market for SC to trade the new product.

References

Adams, J. (2017). The effectiveness of using speech-to-text technology to support the writing of students with learning disabilities. 1-52.

Dodd, A. Z. (2012). The essential guide to telecommunications. Upper Saddle River, NJ: Prentice Hall.

Hsiao, R., Reitmeier, R., Ng, T., Huang, Z., Jordan, M., Kan, E., Kimball, O. (2016). Sage: The new BBN Speech Processing Platform. 1-22.

Khayyat, N. T. (2017). ICT investment for energy use in the industrial sectors. Singapore: Springer.

Olenewa, J. (2014). Guide to wireless communication. Boston, MA: Course Technology/Cengage Learning,

Weckert, J., Lucas, R., & Selgelid, M. J. (2013). Professionalism in the information and communication technology industry. Canberra, ACT: ANU E Press.