No additional charges. It is now possible to switch the speech recognition engine according to the application.
Advanced Media Co., Ltd. (Headquarters: Toshima-ku, Tokyo; Representative Director, Chairman and President: Kiyoyuki Suzuki; hereinafter referred to as "Advanced Media") has added a transcription support application that utilizes AI voice recognition, "AmiVoice ScribeAssist," to medical, parliamentary, and English language services. Added speech recognition engine. Available at no additional charge.

“AmiVoice ScribeAssist” has the No. 1 share in the industry*This is a standalone transcription support application equipped with AmiVoice's voice recognition engine. Can be used in a wide range of situations, both face-to-face and non-face-to-face, such as web conferences, business negotiations, and press conferences.
In addition to the conventional business-oriented speech recognition engines, we have added new speech recognition engines for medical, parliamentary, and English. By selecting the most suitable speech recognition engine for each meeting, you can process more industry-specific language. Furthermore, it can now be used in English conference situations that could not be handled before. Both speech recognition engines are available at no additional charge.
[Speech recognition engine lineup]
Business | It can be used for a wide variety of meetings, regardless of industry, including companies and government offices. |
NEW! Medical | Suitable for meetings that use medical terminology, such as conferences within hospitals. |
NEW! Parliament | Suitable for conversations that use council-specific terminology, such as local councils and committees |
NEW! English | Suitable for meetings and general conversations in English |
[Features]

①
One-stop service from recording to transcription
Everything from audio recording to text editing and output can be completed within one software. Playback of audio and correction of recognition results can be performed using only keyboard operations, greatly reducing the time required for transcription work.
②
Compatible with real-time recognition and batch recognition
In addition to real-time recognition, it also supports batch recognition that captures recorded voice data and converts it into text. It is also possible to transcribe and correct the recognition results at the same time as the meeting.
③
No dedicated server required, audio recording possible from various web conference systems
Since it records audio from your PC, there is no need for troublesome development or settings. Available for all online conferencing systems.
4
Stand-alone type that realizes a secure environment
Since it is a stand-alone model that can perform voice recognition offline (not connected to the Internet), there is no risk of information leakage, and it can be used with confidence even in meetings where confidential information is handled.
⑤
Equipped with various functions useful for creating minutes
・AI speaker identification function
By selecting the speaker during recording, AI will automatically identify the speaker without pre-registration. For one-on-one web conferences, it is also possible to set the speaker for each microphone device.
・Word registration function
By registering words, we can recognize in-house terms and proper nouns with high accuracy. Since you can register multiple lists, you can create the optimal word list for each meeting.
・Keyword setting function
By setting important words in a meeting in advance, keywords in the transcribed remarks are highlighted.
・Tagging function
You can add tags such as "Important Checks," "Decisions," and "ToDo" to speech recognition results with one click. This makes it easier to check the relevant parts while editing text or after outputting to a Word file, etc.
⑥
Supporting communication with real-time subtitle display
・Popup function
The pop-up screen takes into account font size and color universal design, making conversation content more visible.
・Zoom meeting webinar subtitle function
Display conversations during Zoom meetings and webinars as subtitles on the screen. Since speaker information can also be added, it is possible to display the speaker's name at the beginning of the statement.
We will continue to consider adding domain-specific speech recognition engines in response to customer requests.
■AmiVoice ScribeAssist, product page
http://www.advanced-media.co.jp/lp/scribeassist/
* Source: ITR “ITR Market View: AI Market 2020” Speech recognition market – Sales amount share by vendor for meeting minutes (2017-2020 forecast)
Above
Inquiries regarding this matter
Management Promotion Headquarters Public Relations Team
TEL:03-5958-1307

