[vc_empty_space][vc_empty_space]
A prototype of Indonesian dictation component for typing and formatting document using a word processor software
Hoesen D.a, Lestari D.P.a
a Department of Informatics, Institut Teknologi Bandung, Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2014 IEEE.This paper presents our work to build a dictation component in Indonesian language which can be installed to the OpenOffice Writer. The component can reduce the usage of keyboard in making and formatting document by applying an Indonesian automatic speech recognizer (ASR) to transcribe speech into text and a natural language processor to transform text to document format or command. The Indonesian ASR has two main components: an acoustic model and a language model. The acoustic model was trained based on the hidden Markov model (HMM). It was trained by using recordings of 20 native Indonesian speakers, each pronounces about 340 sentences. The total duration of the recordings was about 14.5 hours. The language model based on the n-gram model with the Witten-Bell smoothing was trained by using about 800 sentences containing the recording transcriptions and some punctuated sentences. The dictation component was evaluated for its accuracy and user experience. For a closed evaluation, from 10 participants, the component achieved 89.13% word recognition accuracy. From 10 other participants, 6 out of 10 preferred to use keyboard rather than speech to make and format document. Those 6 who still preferred to use keyboard were willing to use speech if the dictation component could conduct the job effectively and efficiently.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]ASR,Automatic speech recognizers,Dictation,Document formats,Indonesian languages,Natural languages,OpenOffice writer,Speech commands[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]ASR,Dictation,OpenOffice writer,Speech command[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICEECS.2014.7045212[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]