[et_pb_section fb_built=”1″ _builder_version=”4.17.6″ custom_margin=”||0px||false|false” custom_padding=”0px||0px|||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row column_structure=”2_3,1_3″ module_class=”reverse-columns-mobile” _builder_version=”4.17.6″ min_height=”100px” custom_padding=”0px|||||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”2_3″ _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.25.1″ global_colors_info=”{}” theme_builder_area=”post_content”]<\/p>\n
[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.25.1″ text_font=”roboto-regular||||||||” text_text_color=”#003a7c” custom_margin=”||0px||false|false” custom_margin_tablet=”||15px||false|false” custom_margin_phone=”” custom_margin_last_edited=”on|tablet” global_colors_info=”{}” theme_builder_area=”post_content”]Credits: istockphoto\/Igor Kardasov\/ArtemisDiana, Fraunhofer CML[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.17.6″ custom_margin=”0px||0px||false|false” custom_padding=”0px||0px|||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row column_structure=”2_3,1_3″ _builder_version=”4.16″ custom_padding=”0px|||||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”2_3″ _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.25.1″ hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″]During search and rescue operations, for example at sea, the emergency services involved not only have to make the right decisions very quickly and under great time pressure, but also have to communicate a great deal in order to pass on relevant information to all parties. Traditionally, this takes place via VHF, i.e. ultra-short wave, with a reception range of up to 30 nautical miles. This technology has proven to work reliably well over the decades.<\/p>\n
There is one problem, however. \u201cOnly \u2018single-use information\u2019 can be exchanged via radio, which is no longer available afterwards,\u201d explains Maximilian Reimann, Team Leader Maritime Operation Management and research associate at Hamburg\u2019s Fraunhofer Centre for Maritime Logistics and Services (CML). \u201cAlthough radios that allow the last radio message received to be repeated do exist, this doesn\u2019t solve the fundamental problem.\u201d The parties involved are often under a great deal of stress and sometimes overwhelmed by the amount of important information they have to absorb.<\/p>\n
With this in mind, the Fraunhofer CML pursued the idea of developing a support tool for maritime radiotelephony that automatically transcribes and documents the content of radio messages. The challenge is, however, that conventional systems such as Siri and Alexa can only recognise everyday speech. <\/p>\n
\u201cThe maritime industry, however, uses special vocabulary with lots of technical terms and proper names,\u201d he adds. \u201cIn combination with the acoustic conditions on board, conventional voice assistance systems quickly reach their limits, making them unsuitable for use in a maritime context.\u201d In addition, the International Maritime Organisation (IMO) uses the Standard Marine Communication Phrases (SMCP) \u2013 standardised language that serves as pre-formulated examples. \u201cThese haven\u2019t yet become established in practice, however.\u201d <\/p>\n
This is why the CML began developing a speech recognition system specifically for the maritime industry. There were also a few hurdles to overcome here. For example, poor signal quality, loud interference and background noise, different accents, dialects and levels of English all form part of everyday radio communication. Then there are the aforementioned technical terms and abbreviations, set phrases and idioms as well as numerous proper names, such as the names of ships. <\/p>\n
The development phase focussed primarily on maritime terminology. \u201cThis is why the general vocabulary recognition quality isn\u2019t yet as high as with conventional speech recognition systems,\u201d admits Reimann. \u201cIt\u2019s important for us, for example, that it transcribes the correct English spelling of the word \u2018buoy\u2019, and that it doesn\u2019t write \u2018boy\u2019,\u201d he adds.[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ module_class=”dtb-sticky” _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_image src=”https:\/\/www.logistics-pilot.com\/wp-content\/uploads\/2023\/02\/Maximilian-Reimann_500px.png” title_text=”Maximilian-Reimann_500px” align=”center” _builder_version=”4.25.1″ custom_margin_tablet=”” custom_margin_phone=”25px||||false|false” custom_margin_last_edited=”on|phone” hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″][\/et_pb_image][et_pb_text _builder_version=”4.25.1″ header_3_text_color=”#002e5b” text_orientation=”center” custom_margin_tablet=”” custom_margin_phone=”||40px||false|false” custom_margin_last_edited=”on|phone” hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″]<\/p>\n
Maximilian Reimann, Team Leader Maritime Operation Management and research associate at Hamburg\u2019s Fraunhofer Centre for Maritime Logistics and Services (CML)[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.17.6″ custom_margin=”30px||||false|false” custom_padding=”0px||0px|||” bottom_divider_style=”waves2″ bottom_divider_color=”#DFE6EE” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row column_structure=”2_3,1_3″ _builder_version=”4.16″ custom_padding=”0px|||||” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”2_3″ _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.25.1″ hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″ custom_margin=”||50px||false|false”]<\/p>\n
The AI models used were trained using millions of pieces of audio data to ensure a high level of recognition accuracy. These models were then supplemented with maritime data that the CML generated as part of various research projects. \u201cThis allowed us to develop a maritime \u2018standard language model\u2019, which is then enriched and optimised using data from our customers,\u201d continues Reimann. <\/p>\n
Accessing the data was the most difficult part, and training the models was the most time-consuming part, but things are becoming easier. \u201cIn the meantime, around ten hours of audio data is enough for us to adapt a model to a new domain.\u201d This enables audio signals to then be converted automatically into text, i.e. transcribed, and this even works offline. Another advantage is that this makes it possible to evaluate communication content retrospectively, for example to optimise downstream processes. <\/p>\n
\u201cMar FM\u201d already has several customers, although many of them have signed confidentiality agreements. One such customer we are allowed to name is the Vessel Traffic Service Centre (VTS) Fintraffic \u2013 the maritime traffic control centre for the entire Finnish sea area. As part of a research contract, VHF maritime radio traffic was developed here using automatic speech recognition, which converts the radio traffic into text form in real time and makes it available to the vessel traffic control centre. The technology was optimised to recognise English, Finnish and Swedish. <\/p>\n
\u201cA comparable application doesn\u2019t exist anywhere else,\u201d Reimann confirms. The potential, in the industry and beyond, is seen as correspondingly large. \u201cApplications for the offshore wind industry, the oil and gas sector or aviation are also conceivable,\u201d he adds. \u201cUltimately, our application works wherever aural information is exchanged.\u201d (cb)<\/em>[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ module_class=”dtb-sticky” _builder_version=”4.16″ global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_blurb title=”Facts” _builder_version=”4.16″ header_font=”|||on|||||” header_text_color=”#ffffff” header_font_size=”16px” text_orientation=”center” custom_margin=”||20px||false|false” custom_margin_tablet=”” custom_margin_phone=”25px||||false|false” custom_margin_last_edited=”on|phone” custom_css_blurb_title=”display: inline-block!important;||background: #002754!important;||padding: 5px 13px 3px 13px!important;||position: relative!important;” border_width_bottom=”1px” border_color_bottom=”#002754″ global_colors_info=”{}” header_text_color__hover_enabled=”on|desktop” header_text_color__hover=”rgba(255,255,255,0.71)” theme_builder_area=”post_content”][\/et_pb_blurb][et_pb_text _builder_version=”4.25.1″ hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″]<\/p>\n <\/p>\nFraunhofer Centre for Maritime Logistics and Services CML<\/h2>\n