Voiscope IVR System
Interactive Voice Response (IVR) is a technology that allows a computer to interact with humans through the use of voice and DTMF tones input via a keypad.
In telecommunications, IVR allows customers to interact with a company’s host system via a telephone keypad or by speech recognition, after which services can be inquired about through the IVR dialogue.
IVR systems can be used for mobile purchases, banking payments and services, retail orders, utilities, travel information, weather conditions etc.
Our IVR system can respond with pre-recorded or dynamically generated audio to further direct users on how to proceed. Our IVR system also can handle large call volumes and also used for outbound calling.
It also supports CTI, ASR and TTS Integrations.
Voiscope Dialer System
In Call Centers there are several dialling modes depending on how the call is placed. Preview Dialer, Auto Dialer, Power Dialer, Predictive Dialer are well known models.
Preview dialing enables agents to first view the available information about the customer and decide when to place the call. In addition to the information about the customer, agents may also view all the history of the customer with the contact center. After viewing the information about the customer, the agent requests the system to make the call.
Auto dialing enables telemarketers, sales teams, and call centers to dial a list of phone numbers automatically and completely hands-free, thus, saving them valuable time and energy that would otherwise be wasted dialing by hand. It does not transfer call to agent.
Power dialing is suitable for all campaigns, from customer care follow-up calls to telemarketing. For example, power dialing is useful to call predictive dialing contacts that resulted in nuisance to ensure that an agent is available to talk to the customer.
Predictive dialing is a state-of-the-art pacing mode used to call a large number of customers within a short period of time. Predictive dialing optimizes the time of agents by reducing the idle times between connected calls and freeing agents from dialing calls.
Voiscope Call Recording System
Voice Recording Systems are systems which record phone calls with their call informations like date, time, phone number, internal number, CTI data and so on.
The technical specifications expected from an advanced Voice Recording System are briefly described as having a Web-based and easily manageable interface,
distributed operation, detailed and flexible reporting capability, capability of recording from network sniff, supporting VoIP protocols like SIP, H323, RTP, SRTP and so on.
integrating into hubs such as AVAYA, CISCO, GENESYS.
All of these features and much more are available in the Voice Recording System we have developed.
Voiscope Speech Analytics
Speech Analytics Systems are systems that convert the contents of voice recordings made into texts and save them in the database. In this way they can present reports on the contents of the calls.
Special training is provided for each vocal recording op- eration to ensure high performance. In this way the recognition performance ratio is increased to 90% and above.
The technical specifications expected from an advanced Speech Analytics System are briefly the ability to run at high channel capacity with high recognition rate, to provide detailed reports on call content, and to present them all in an easy-to-use, understandable modern web interface.
All of these features and much more are available in the Speech Analytics System we have developed.
Deep Learning is used.
ASR Demo
Voiscope ASR
Automatic Speech Recognition (ASR) Systems are systems that process digital audio data to transform the audio content into text.
Call Steering is one of the common usage areas by integrating with IVR systems so that callers can receive voice input instead of dialing and transfer the call to the appropriate menu or customer representative quickly.
They are language dependent systems. It is necessary to create a separate model for each language, so training with the data of that language is necessary.
The technical specifications expected from an advanced ASR system are having Web API that is easy to use for software developers and being multichannel and capable of performing more than one operation at the same time with a minimum of 90% accuracy.
All of these features and much more are available in the ASR System we have developed.
Deep Learning is used.
TTS Demo
Apart from the demo models below, we can customize your model in a very short time with the voice of the person you want. You can contact us for this. All we need is to read the announcements we give to that person.
Voiscope TTS
TTS (Text To Speech) Systems are systems that convert text content into digital audio data.
By working in conjunction with IVR systems, it is one of the common usage areas to read the announcements that need to be read dynamically by entering text without a sound file.
They are language dependent systems. It is necessary to create a separate model for each language, so training with the data of that language is necessary.
The technical specifications expected from an advanced TTS system are that it can produce sounds within the shortest time possible
without giving the sense of robot with the correct pronunciation, accent and tone for the languages they support with an easy-to-use Web API.
All of these features and much more are available in the TTS System we have developed.
Deep Learning is used.
REQUEST DEMO NOW
If you want to get more detailed information about our products (IVR, Dialer, Voice Recording, Speech Analytics, ASR, TTS) and live test, please fill out the form below and we will get back to you shortly.
ONGOING R&D PROJECTS
1) CONTACT CENTER
Cloud based, omni channel Call Center project that supports Web RTC, Social Media and Web Chat.
2) EMOTION DETECTION
It is the system that detects the emotional state of speech from the audio signal. These systems determine the emotional state of the voice signal by combining the prosodic characteristics of the voice signal with the statistics of the words used in the speech content. The use of Emotion Recognition in voice recording systems plays an important role in improving call center service quality. Deep Learning is used.
3) SPEAKER VERIFICATION
It is the system that verifies the speaker identity from the audio signal. It works by integrating with IVR systems so that the identity of the caller is automatically verified. Text Dependent Speaker Verification is used for input to IVR systems. Text Independent Verification is used in Call Center systems to automatically determine the identity of customers. In this way, it is possible to identify malicious persons who have acquired information of the customer. Deep Learning is used.
4) SPEAKER DIARIZATION
It is the system that finds out who is talking to when the audio signal is talking. It is determined who spoke and when they talked without using any information about the number of speakers and who the speakers are. Deep Learning is used.
CAREER
If you want to work with us to take part in our R&D projects, you can send your CV to us for evaluation.
CONTACT
ADDRESS
Yildiz Technical University Davutpaşa Campus Teknopark D2 Block No:2B03 Esenler / Istanbul - Turkey, 34220
info@voiscope.com
PHONE
+(90) 0850 532 75 04
Send Message
Voiscope Ltd.
YTU Davutpaşa Campus Teknopark D2 Block No:2B03 Esenler / Istanbul - Turkey, 34220
E-Mail: info@voiscope.com
Phone: +90 0850 532 75 04