Advanced Media Co., Ltd. AI voice recognition subtitle system “JTAC-ACP” developed by TV Asahi Create Cooperates with AmiVoice voice recognition API

Advanced Media Co., Ltd.
AI voice recognition subtitle system “JTAC-ACP” developed by TV Asahi Create Cooperates with AmiVoice voice recognition API

Advanced Media Co., Ltd. (Headquarters: Toshima-ku, Tokyo, Chairman and President: Kiyoyuki Suzuki, hereinafter referred to as Advanced Media)’s voice tech platform “AmiVoice Cloud” for developers that provides voice-related technologies centered on speech recognition. AmiVoice voice recognition API provided by Platform (Amivoice cloud platform)” is AI voice recognition developed by TV Asahi Create Co., Ltd. (Headquarters: Minato-ku, Tokyo, President: Atsushi Takahara, hereinafter TV Asahi Create) Adopted for the subtitle system “JTAC-ACP”.
“JTAC-ACP” is an AI voice recognition subtitle system that enables the production of live subtitles for TV programs, which requires advanced typing skills, with a short period of software operation training. By using a proofreading terminal for the results of automatic
transcription using AI speech recognition, you can proofread to your desired subtitle specifications.
From October 2022, the actual operation of TV Asahi will start, and the work efficiency of real-time subtitle production has been greatly improved.
[“JTAC-ACP” speech recognition terminal]
[Image 1

From single calibration to multiple calibration, it can be used for various purposes.
[“JTAC-ACP” calibration terminal]
[Image 2

You can proofread the text automatically transcribed by the speech recognition terminal with a simple operation.
The AmiVoice speech recognition API provided by the “AmiVoice Cloud Platform” has been adopted as the AI ​​speech recognition engine used for automatic transcription of “JTAC-ACP”. By converting natural spoken Japanese into text with high precision and speed, it simplifies proofreading work and greatly reduces the burden of typing work. In addition, the usage fee for the AmiVoice voice recognition API is a pay-as-you-go system, so customers with short usage times can use it easily.

[Features of AmiVoice speech recognition API]
1. Voice recognition market share No. 1 (*). Convert natural spoken words into text with high accuracy
AmiVoice is a high-precision and high-speed speech recognition engine with more than 20 years of accumulated know-how and data. Converts natural spoken words into text with high accuracy, regardless of speaking speed, intonation, or accent.
2. High-quality voice recognition available at a low price
Pay-as-you-go billing only for the amount of time spoken, not the amount of time recorded. The billing unit is also rounded up in units of 1 second, and there is no calculation. You can use a high-quality speech recognition engine at the lowest price in the industry. 3. Vocabulary filtering suitable for business use
We use a language model that is strong for business use, omitting inappropriate terms that are not used in business, business, or general conversation. Since unnecessary words are omitted, it can be used safely in a wide range of situations.
4. Achieve high recognition rate with engine that can be selected according to industry and application
In addition to the “general-purpose engine” that can be used in various scenes, we have prepared an engine that specializes in technical terms such as the medical field and industry terms. The recognition rate is greatly improved by selecting the engine according to the usage scene.
By using the dictionary registration function, it is possible to convert in-house terms and proper nouns into text with high accuracy. 5. Automatically remove hesitation such as “uh” and “uh”
Automatically removes hesitation (fillers) such as “uh”, “that”, and “that”. Punctuation marks and question marks are also added
automatically. Supports the creation of more accurate and
easy-to-understand spoken language sentences.
[Image 3

■ AmiVoice Cloud Platform
TV Asahi Create has developed “JTAC-ACP” with the aim of solving the difficult problem of securing and training human resources, which has traditionally been a problem for live subtitles of TV programs. Advanced Media will continue to actively publish and utilize various APIs and development kits, and will expand its efforts to promote open innovation and create new usage scenes with a wide range of partners.

■ AI voice recognition subtitle system “JTAC-ACP”
For product details and inquiries about AI voice recognition subtitles, please contact the following email address.
[Contact email address]
[TV Asahi Create HP]
*Source: ecarlate “Voice Recognition Market Trends 2022” Voice Recognition Software/Cloud Service Market
that’s all
Advanced Media Co., Ltd.
PF D&O department

Details about this release:

Leave a Reply

Your email address will not be published. Required fields are marked *

%d bloggers like this: