Call Center Solutions
Onkyo IVR
Onkyo IVR is an AI-based automated phone reception and dispatch system.
Simply transfer
Easy Installation
Onkyo IVR allows callers to simply transfer calls to a call center system with many restrictions. It can be implemented in as little as two weeks.
Automatic voice dictation
Automatic
Onkyo SPEECH, a proprietary voice recognition engine, was developed. The process from telephone reception to transcription is fully automated.
personnel reduction
Leave the automated reception to Onkyo IVR. Since the receptionist can check the details of the receptionist's message in a dedicated viewer, operators can only respond to problems when they occur, reducing the number of personnel needed.
Operates 24 hours a day, 365 days a year
Continuous operation 24 hours a day, 365 days a year eliminates the need for three shifts. It improves the quality of service and the efficiency of operations.
Individual Customization
Onkyo IVR can be individually customized to learn up to 80% recognition rate at no additional cost.
By combining (fusing) Onkyo SPEECH, our proprietary speech recognition technology, with AWS's Amazon Connect, we are solving call center problems that require improved service quality and receptionist efficiency.
Characteristics
1. incoming call
When a call comes in from an end user, Onkyo IVR will respond. The necessary information is interviewed and answered in a step-by-step manner.
Analysis by Onkyo IVR
Stores and analyzes call data, converts voice to text, and registers personal information in a database.
3. check the contents in the viewer
The operator reviews the content in a dedicated viewer and responds only to problems or those that require further action.
IVR takes the primary receptionist, and voice data is instantly converted to text and stored in the database. This is the secret to reducing operator headcount.
structure
voice recognition
Speech recognition consists of "acoustic model" and "language model" projections. It utilizes speech data from 10,000 speakers, totaling more than 700 hours of speech data.
End-user statements are subjected to acoustic analysis and then recognized through a search algorithm based on a speech recognition model learned from training data.
Speech Recognition Configuration
Image of improved speech recognition accuracy
Language Model Update
Text learning of incorrect parts from speech recognition results.
Acoustic model update
Transcriptions of industry/environment-specific audio will be transcribed and made available for study.
Onkyo IVR Security
Onkyo IVR is a private cloud and secure communication. Onkyo IVR is a highly secure security system that maximizes the handling of personal information by restricting access.
pickup reception
Return Receipt
secretarial service
attendance follow-up
Shift Confirmation
Texting of calls
Industries that require
For this type of business
It is suited for business types where the content of the interview with the customer is roughly fixed. It is also possible to switch the flow of the interviewing process to one that is more in line with the content selected during the interviewing process.
*Please allow 2 weeks for installation.
Monthly Package
Usage Fees
Conference Accepted Papers
Onkyo IVR's speech recognition has been the subject of papers presented at conferences.
【2021】
O-COCOSDA 2021 Best Paper AwardNobuya Tachimori (Onkyo Corporation, Japan),Sakriani Sakti and Satoshi Nakamura(Nara Institute of Science and Technology, Japan)MULTI-ENCODER SEQUENTIAL ATTENTION NETWORK FOR CONTEXT-AWARE SPEECH RECOGNITION IN JAPANESE DIALOG CONVERSATION
https://ieeexplore.ieee.org/document/9660580
FAQ
There is no limit, but if you need more than 10 lines, please contact us at the time of inquiry.
Depending on the customization of the flow, if it consists only of fixed attributes such as name and address, please allow two weeks.
It is possible. For voice recognition only, Onkyo SPEECH API is provided.
Please contact us for more information, as it is possible to consult depending on the usage flow rate.
We evaluate the recognition rate by WER (Word Error Rate) and the recognition rate must be 85% or more. 80% or less, we will accept the text study together with the text study free of charge.
The standard time frame is 2 weeks for text study and 3 weeks for audio study.
Possible. Please contact us for specific costs.
It is possible. Please contact us to discuss the best plan for your company's system situation.