(AmiVoice Cloud Platform)

Webinars
  • HOME
  • Webinars
  • Are you choosing AmiVoice x AWS based solely on "recognition rate"? The new standard for utilizing speech recognition in the age of AI agents.

Are you choosing AmiVoice x AWS based solely on "recognition rate"? The new standard for utilizing speech recognition in the age of AI agents.

9 / 17 (Thu.)

This seminar will introduce the latest trends in AWS's AI generation services and the functions and use cases of the AmiVoice API, as well as the speech recognition technology required in the era of AI agents and how to utilize it.

This time, we'll focus on "input data quality," which is crucial for AI agents to make accurate decisions and take action. We'll introduce the latest trends in AWS's AI generation services, such as Amazon Bedrock AgentCore, Kiro, and Amazon Quick, and explain the high-precision speech recognition, real-time capabilities, and AI usability required for input to AI agents. Furthermore, we'll introduce technical points and use cases for utilizing additional information from the AmiVoice API to improve response speed.

If you are considering developing or using AI agents in your business, or if you are interested in developing services that combine AWS and speech recognition, please join us.

■ What you will learn from this seminar
• Latest trends in AI agent utilization and developments in AWS's generative AI services
• The importance of input data quality in supporting AI agent decision-making and execution.
• Features of the AmiVoice API and key points when integrating with AI agents
• Applications that leverage high-precision speech recognition and real-time capabilities

■ Recommended for people like this
・I am considering developing and utilizing AI agents.
・I want to know the latest trends in AWS's generative AI services.
・I am interested in developing services that combine speech recognition and generative AI.
・I want to use voice input as a source of information for AI agents.
・I am considering introducing and utilizing the AmiVoice API.

TitleAmiVoice × AWS
Are you choosing based solely on "recognition rate"?
New Norms for Speech Recognition in the Age of AI Agents
DateThursday, September 17th, 4:00 PM - 5:00 PM
VenueZoom
Entry FeeFree
TargetThis is for those considering developing and utilizing AI agents, those interested in AWS's generative AI services and their application to business, and those interested in integrating speech recognition APIs with AI agents.
way to participateIf you apply using the form on the right, you will receive an automated confirmation email.
MessageSession 1: Trends in AI agent utilization and the latest developments in related services on AWS
Speaker: Yuki Iida (Amazon Web Services Japan, LLC)

The use of generative AI is rapidly evolving from single-function applications such as text generation and summarization to "AI agents" that autonomously make decisions and execute multiple steps.
In this session, we will cover the latest trends in AI agent utilization and introduce the latest developments in AWS generative AI services, including Amazon Bedrock AgentCore, Kiro, and Amazon Quick.
I will also discuss the importance of input data quality in making better use of AI agents.


Session 2: What kind of speech recognition is needed in the age of AI agents? - AmiVoice API functions and key points for utilization -
Speakers: Mao Kawamura and Ai Nagashima (Advanced Media, Inc.)

For an AI agent combined with speech recognition to make correct decisions and execute tasks, "high-precision speech recognition" that can accurately transcribe important words is essential. In addition, "real-time capabilities" to enable natural conversation and "AI usability" to provide information that leads to task execution are also indispensable elements.
In this session, we will introduce the features and use cases of the AmiVoice API, focusing on these three requirements. Furthermore, from a technical perspective, we will explain how to utilize additional information and practical points for improving response speed.
Notes*This seminar will be held online (webinar).
*Please note that filming or recording of this webinar is prohibited.
*Content may change without notice.
*Applications from competing companies may be rejected.
Contact UsAdvanced Media, Inc. Webinar Office
Mail: ami-pfdo-webinar-ml@advanced-media.co.jp

Use API for Free

Try out recognition accuracy

For engines, please try the latest End to End. If you would like an engine specialized for industries such as healthcare, insurance, or finance, please select Hybrid and choose your language model and acoustic model.

Engine

Language

Language model

Acoustic model

Example sentences will be displayed.
This is sample text. Your voice input will go here.
残 り 30 seconds left

Terms of Use for
AmiVoice Speech Recognition Demo

Select the language, language model, and acoustic model you want to try, press the "Start speech recognition" button, and start speaking.
You can speak freely or read out example sentences and the recognition results will be displayed.

*If you change the language, language model, acoustic model, or use application, please press the "Start speech recognition" button again.

Points to note

  • By using this service, you are deemed to have accepted the terms of use.
  • Supported browsers are the latest versions of Windows (Chrome, Firefox, Microsoft Edge), Android (Chrome, Firefox, Microsoft Edge), Mac (Safari), and iOS (Safari).
  • Depending on the browser, the recording quality may be poor. If you feel that the quality is not good, please try using a different compatible browser.
  • Please enable the microphone function in your browser's security settings.
  • The trial time for this service is 1 seconds per trial. If you would like to use it again, please click "Start speech recognition" button.
  • Voice data and text data may be used to improve speech recognition performance.
×