Contact center operations
Dramatically more efficient
AmiVoice Communication Suite converts all calls into text in real time,
Automate response quality evaluation, sentiment analysis, summary generation, etc.
We provide thorough support for improving the efficiency of contact center operations.
* Source: ITR "ITR Market View: Image and Voice Recognition Market 2024" Voice Recognition Market -
Sales share by vendor for contact center operations (FY2024 forecast)
Over 90,000 licenses!
All calls converted to text
Resolving Contact Center Issues
All conversations between operators and customers are converted into text and generative AI is used to significantly reduce the work of creating response histories.
The monitoring and chat functions allow for rapid escalation and thorough follow-up with operators.
(VOCs)
By converting all calls into text, you can now use all of the customer feedback that you have previously missed for marketing analysis.
Efficiency
This enables the resolution of "said/not said" disputes and the rapid identification of risky calls, strengthening compliance.
Four reasons to choose AmiVoice
The voice recognition engine has accumulated resources based on numerous implementation results, and converts voice to text with extremely high accuracy. Technical terms and abbreviations can also be converted smoothly and with high accuracy.
easy-to-use interface
Not only does it have intuitive operability that allows you to efficiently access the information you need, but it also comes equipped with functions optimized for contact center operations.
Achieve more efficient operations
The API allows us to link with a variety of external systems and other companies' cloud services, enabling us to flexibly build systems that meet our customers' ideals.
It can be operated in a variety of ways to suit the customer, such as cloud or on-premise, real-time or batch recognition, etc. It supports both server recognition and client recognition.
Abundant functions
Equipped with a wide range of functions, it thoroughly supports improving the efficiency of contact center operations.
In real time
Call Text Display
- Real-time processing
Real-time call text display
Call data is displayed in text format for visualization.
You will be able to check the voice recognition results in real time and use the call filter (pop-up) function.
Collaboration with generative AI
Streamline post-processing operations
- Real-time processing
- Batch processing
Streamline post-processing work by linking with generation AI
After the call ends, the text of the call data is automatically generated and processed by AI, and then displayed on the screen.
You can copy the results with one click and paste them into the required place such as a CRM system, or you can automatically link them using an API.
It is also possible to select the generative AI model to use for each item, such as "summary," "FAQ creation," "address," and "phone number."
Multiple calls with seating plan
Real-time visualization
- Real-time processing
Real-time visibility of multiple calls on seating chart
SV can check the call content of all operators simultaneously in the seating chart view.
Quality of response for every call
Automatic scoring
- Real-time processing
- Batch processing
Automatically score the quality of every call
It can automatically evaluate whether or not NG word detection, important matter explanation, speaking speed, timing of speech, etc. are appropriate. Evaluations are not influenced by the SV's subjectivity, and evaluations can be made for all calls. Evaluation results can be viewed on the screen and can also be output as CSV data.
Keyword spotting
Automatic pop-up of documents
- Real-time processing
Keyword spotting
Automatic pop-up of documents
By using voice recognition to recognize keywords that have been registered in advance, a pop-up will appear, enabling knowledge linking such as FAQ searches, file recall, and web searches.
Furthermore, by using the topic category function in combination, you can flexibly execute commands based on multiple keywords, allowing you to display more contextual, detailed, and appropriate materials.
Voice recognition and emotion analysis results
See it at a glance
- Real-time processing
- Batch processing
Voice recognition and emotion analysis results can be checked at a glance
The recognized call data is displayed as text and waveform, and the call data can be viewed, searched, edited, and graded. Since the text and audio are managed in association with each other, you can easily check the audio of the searched part.
With the help function
Notify SV immediately of the situation
- Real-time processing
Help function immediately notifies SV of the situation
Operators can send help notifications to SVs. The notifications are displayed on the SV's screen, allowing them to visually confirm the notifications.
In all conditions
Quickly find the call you need
- Real-time processing
- Batch processing
Quickly find the calls you need by any criteria
In addition to keyword searches, you can also narrow down search data by any other criteria, allowing you to pinpoint the calls you need.
Technical terms can be easily registered
Improved recognition accuracy
- Real-time processing
- Batch processing
Improve recognition accuracy for technical terms with simple word registration
Recognition accuracy can be improved by registering words such as product names and technical terms.
Customer Harassment Detection and Countermeasures Package
Six functions of the Communication Suite have been customized for customer harassment detection and countermeasures.
A special package that combines a locally generated AI customer harassment information extraction model.
We provide strong support for customer harassment countermeasures, reflecting the know-how of 500 companies that have implemented our system.
Please feel free to contact us with any questions.
[With examples] Product introduction materials that can be understood in 5 minutes
Generative AI x Contact Center Optimal Solution
We use AI to easily extract various information from text-converted call data. Using our knowledge and expertise backed by a track record of contact center implementation in a wide range of industries,
You can utilize generative AI specialized for contact center operations.
AI generated results such as summaries are displayed instantly, allowing for smooth operation.
Call summaries, Q&A, and customer information extraction are automated and displayed on the operator's screen. This reduces the number of screen transitions and copy-and-paste operations, significantly cutting the time required to create call logs. A summary of the conversation between the operator and the customer can also be viewed on the supervisor's screen, enabling smoother support.
Dramatically reduce the time required to create response history
Flexible connection to various generative AI services
In addition to the secure local LLM (local generation AI) for contact centers, the latest generation AI services can also be connected. You can use them separately or in a hybrid configuration depending on your needs.
＆ High security
Since the generation AI (LLM) can be built in a local environment, call data is never sent to an external party, allowing you to use it with peace of mind.
Unique customizability
We create a generative AI model specifically for you by fine-tuning according to your purpose, and the output from the generative AI can be made closer to the optimum content for your business.
High accuracy
As a result of fine tuning, accuracy can be significantly improved compared to controlling output by adjusting prompts alone.
latest technology
You can use the latest generative AI, which is evolving every day.
High functionality
It can be linked to generative AI services with various functions and features. You can choose the generative AI service that best suits your needs.
Free prompt settings
Prompt Engineering allows you to flexibly utilize generative AI services for a variety of applications.
Collaborative generative AI services
API integration with a wide range of external systems
It can easily be linked with various services, making your work more efficient.
- Real-time processing
- Batch processing
Streamline post-processing work by linking with generation AI
After the call ends, the text of the call data is automatically generated and processed by AI, and then displayed on the screen.
You can copy the results with one click and paste them into the required place such as a CRM system, or you can automatically link them using an API.
It is also possible to select the generative AI model to use for each item, such as "summary," "FAQ creation," "address," and "phone number."
- Real-time processing
- Batch processing
API integration: CRM system
You can display the call recognition results in real time on the CRM screen.
CTI integration: CRM system
By customizing the CRM system, such as by adding a "voice recognition result display button," it is possible to display the call details screen with one click from the customer management screen. By linking with the CTI system, each system can be managed with the same call ID, so customer management and call details data can be automatically linked without the need for operators to manually copy and paste as in the previous pattern.
- Real-time processing
- Batch processing
API integration: Summary system
It is possible to link with an automatic summarization system.
During the call, speech recognition is performed in real time, and after the call ends, an automatic summary system* performs a summary. The results can be partially corrected as necessary, and can be attached to CRM with one click, which is expected to significantly reduce the time it takes to create a response history.
System
- Real-time processing
- Batch processing
API integration: Text mining system
Many call centers use call history as the source data for VOC analysis, but there are many cases where sufficient VOC cannot be obtained due to the operator's subjective opinions and necessary information being omitted. By converting the conversation into full text and analyzing it, it is possible to grasp even the detailed needs of customers that could not be obtained before, and use this information for planning new services, etc.
Proven operational IP-PBX and cloud PBX services
- Avaya Communication Manager Series
- OKI CTstage series
- NEC SV Series
- NEC Aspire Series
- Genesys PureConnect
- Genesys PureCloud
- Genesys Cloud
- CT-e1
- Fujitsu CL series
- Fujitsu LEGEND V Series
- Link BIZTEL
- AmazonConnect
- Bright Pattern Contact Center
- Collabo @nyplace
- Asterisk
We have experience with cases other than those listed above. Please contact us for details.
Introduction Results
Number of incoming calls8000 increase
The average post-processing time per call was reduced from 1 seconds to 56 seconds for inquiries and from 19 seconds to 35 seconds for main exchange operations, achieving an improvement rate of more than 16% compared to the previous manual input method. The number of calls received increased by approximately 50 per month, and the number of overflow calls decreased.
Improved conversion rate from 24% to 50%
Using voice recognition, we focused on the effect of the order of topics and the weighting of topics in sales talks on the success rate, and conducted a comparative analysis between high and low performers. We were able to easily and quickly extract the points of interest, and by implementing improvements, we were able to double the success rate.
Easy VOC extraction
We have implemented an operation that allows us to understand customer feedback by adding tags such as "customer feedback" to specific utterances such as "Thank you for your valuable opinion" and searching for calls that have been tagged.
Talk script revision
Customer "delight" increased fourfold
Emotion analysis was used to compare the difference in customer emotions before and after improvements were made to the conversation script used to ask about cancellation reasons. After the improvements, customer happiness was four times greater, and the revised conversation script enabled responses that were more sympathetic to customer emotions.
Approximately 150 times more monitoring
It has become possible to monitor 150 times as many calls in half the time it took before. In addition, the call content is automatically scored using an evaluation function based on HDI standards, which has made feedback clearer and led to quality improvements.
Guests’ Feedback
Customer Harassment Prevention Manual x Voice Recognition System to Improve Customer Center's On-site Capabilities
HimejiReduced overtime hours spent on recording telephone consultations by 66%
Achieving VOC acquisition and improving customer service quality by introducing cloud services
Automatic call evaluation function for monitoring improves the efficiency of evaluation work and response quality
Real-time voice recognition dramatically improves the efficiency of call center operations
The first use case in the insurance outbound telemarketing industry!
Greatly streamline the process of checking successful calls!
FAQ
Generally, when speaking politely and clearly, like a call center operator, the recognition rate is over 90-95% on average. On the other hand, when speaking casually, such as when speaking to a customer or on an internal line, the average rate is around 80-90%.
It is calculated by comparing what was actually said with the text of the speech recognition results.
If every single character matches, the recognition rate will be 100%. If characters are inserted, deleted, or replaced, the recognition rate will decrease.
For example, if "Osewa ni namasu" is recognized as "Osewa ni shite natte," then for the eight correct characters, one character is replaced by "su" to "shi" and one character is inserted, resulting in a recognition rate of (8-1-1) ÷ 8 = 75%.
Yes, it is possible. Technical terms and proper nouns can be recognized by voice recognition by "word registration." You can easily register words yourself.
Differences in intonation can be recognized without any problems. However, for words and phrases specific to dialects, such as saying "thank you" instead of "thank you," it is necessary to register the words and train the speech recognition engine.
The following methods can be expected to improve recognition rates.
■ Word registration
Accuracy can be improved by registering technical terms and company terminology. Customers can easily register words themselves.
■ Individual tuning of the voice recognition engine
Our expert staff can improve the recognition rate by having the speech recognition engine learn the content of conversations at your contact center.
■ Operational improvements
You can improve the recognition rate by paying attention to the following:
Speak clearly and articulately
Set the recording volume appropriately
Maintain an appropriate distance between the headset and your mouth
Yes, we can do a proof of concept (POC) with a small number of seats. We can also provide you with pre-recorded voice data to test voice recognition. For details,Contact.
Yes, it is possible. We will make the best proposal based on your budget and scale. For details,Contact.
Depending on your security requirements, you can choose between a local LLM that can be used in a local environment or a cloud-based generation AI. Local LLM does not require sending call data to an external cloud, and can be processed safely within the company's network. This reduces the risk of data leaks, even for highly confidential customer information and call content.
AmiVoice Communication Suite uses a speech recognition engine specialized for contact center conversations. Utilizing the extensive learning data accumulated through implementation in over 600 companies, it can convert call content into text with high accuracy.
It also supports individual tuning to suit your business operations and call characteristics, further improving speech recognition accuracy. It also supports the use of generative AI to summarize call content, generate Q&A, and automatically extract customer information. Depending on your security requirements, you can choose between local LLM, which can be used in a local environment, or the latest cloud LLM, and even combine the two for hybrid operation.
It supports both cloud and on-premise systems. You can also choose between real-time processing and batch processing. It can be flexibly constructed to suit your needs and environment. For details,Contact.
AmiVoice®
MediaScriber Cloud
Upload audio files to convert them into text. Recommended for those who want simple functions and low cost operation.
Service can be started in as little as five business days after application. You can use it as much as you need, whenever you need it.
By picking up the necessary call recordings and processing them with voice recognition, operation can be carried out at low cost.
You can easily convert audio files to text by simply uploading them from the web. No complicated operations are required.
News
-
2026/01/22Webinars[December 4th] "Concepts and Usage" of Automated Quality Evaluation to Increase Monitoring Efficiency - Key Points to Remember When Using Automated Quality Evaluation and AI
-
2025/11/13News[Campaign in progress] Get 3 months of "AmiVoice CQM Assist," an automatic report creation tool for contact centers evaluating customer service quality.
-
2025/11/12NewsImplemented a new function, "AI Multi-Stage Inference," that utilizes multiple generative AIs to enhance processing.
AmiVoice is a contact center
We will solve all your problems!
Please feel free to contact us with any questions.
[With examples] Product introduction materials that can be understood in 5 minutes
We also recommend these services:
VoiceSpot's cloud service automates telephone answering. It is suitable for a variety of situations, including contact centers, order desks, and main lines.
~POWERED by PERSOL BUSINESS PROCESS DESIGN~
Utilizing voice recognition results to streamline monitoring operations. Automatic creation tool for customer service quality evaluation reports for contact centers.