AmiVoice is provided by the voice recognition development platform "AmiVoice Cloud Platform" of Advanced Media Co., Ltd. (Headquarters: Toshima-ku, Tokyo, Chairman and President: Kiyoyuki Suzuki, hereinafter referred to as "Advanced Media"). Speech recognition API has been adopted in "Smartphone Mojiko," the smartphone-compatible version of the transcription editor "Mojiko" developed by TBS TV Co., Ltd. (Headquarters: Minato-ku, Tokyo, President and CEO: Takashi Sasaki, hereinafter referred to as TBS TV) Sales have started from Yoshizumi Information Co., Ltd. (Headquarters: Chiyoda-ku, Tokyo, President and CEO: Harumichi Akita, hereinafter referred to as Yoshizumi Information).
"Smartphone Mojiko" is a smartphone version of the transcription editor "Mojiko" developed by TBS Television. The design is optimized for transcription work, reducing work time by approximately 50% (according to TBS TV research).
The audio/video files and other materials collected during interviews are automatically converted into text using a speech recognition engine, and the recognition results are linked to the audio and saved on the smartphone. Speech recognition engines can be selected according to the type of speech you want to recognize and the purpose.
Following "Mojiko", "Smartphone Mojiko" has also adopted the AmiVoice speech recognition API provided by "AmiVoice Cloud Platform".
[Features of AmiVoice speech recognition API]
1. No.1 voice recognition market share
■
. Convert natural spoken words into text with high accuracy
AmiVoice is a highly accurate and high-speed speech recognition engine with over 20 years of accumulated know-how and data. It converts natural spoken words into text with high accuracy, regardless of speaking speed, intonation, or accent.
2. Vocabulary filtering suitable for business use
We use a language model that is strong for business use, eliminating inappropriate terms that are not used in work, business, or general conversation. Because unnecessary words are omitted, it can be used with confidence in a wide range of situations.
3. Achieving high recognition rates with engines that can be selected according to the industry and application
In addition to "general-purpose engines" that can be used in a variety of situations, we also have engines specialized for specialized and industry terms such as those used in the medical field. Recognition rates can be greatly improved by selecting the engine according to the usage scenario.
By using the dictionary registration function, it is possible to convert in-house terms and proper nouns into text with high accuracy.
4. Automatically delete hesitations such as “um” and “um”
Automatically removes fillers such as "um," "so," and "that." Also, punctuation marks and question marks are automatically added. Supports the creation of more accurate and easy-to-understand spoken sentences.
5. High quality voice recognition available at low cost
Pay-as-you-go billing based only on the amount of time spoken, not the amount of time recorded. Billing units are not rounded up to the nearest second. You can use a high-quality speech recognition engine at the lowest price in the industry.
| (AmiVoice Cloud Platform) | |||
| APP & WEB SOLUTION | https://acp.amivoice.com/main/ | ||
In the television and radio industry, a huge amount of transcription work is carried out every day, placing a heavy burden on program production sites. "Mojiko" was developed to improve the efficiency of transcription work and reduce the workload in a wide range of situations, including the television and radio industry, print media, and meeting minutes.
Advanced Media will continue to actively release and utilize various APIs and development kits, and work with a wide range of partners to expand our efforts to promote open innovation and create new usage scenarios.
[Transcription editor “Mojiko”]
Using an AI speech recognition engine, we automatically convert materials such as audio and video files collected into text without taking the actual time of the material length. Misrecognitions can be instantly corrected and edited by humans using a dedicated editor. In addition, with the assumption that it will be used in the field of program production, it is equipped with functions such as linking with time code, displaying thumbnail images, setting speakers, and inserting notes, so anyone can operate it intuitively and easily. Masu.
https://mojiko.ai
*Source: ITR “ITR Market View: AI Market 2021” Voice recognition market sales share by vendor (2015-2021 forecast)
Above
