Core Technologies

• What is Speech Recognition?

• What do you mean by “machine”? Can I put SR on any device?

• So, does that mean SR will understand whatever I say? How does it work?

• What will happen when something that is not on the list is spoken?

• What is the success ratio for this product?

• It is hard for us to offer an SR service for our mobile apps, since they can also be used offline. Can we just use text-to-speech in the app?

• Can I use SR on the cloud?

• Does SESTEK SR work on virtual machines?

• Which operating systems do you support?

• Which IVR clients do you support?

• How long does it take to implement SR?

• Can we create our own recognition list?

• What should I do if I have questions or problems with SR?

• What is Text to Speech?

• Where can i use TTS?

• How does it work anyway?

• So why should i use TTS? Isn’t a robot voice annoying to customers or users?

• TTS is a good product but sometimes hearing two different voice in IVR (the real speaker and TTS voice) sounds a little less elegant. What should we do about it?

• Can TTS read everything that we want?

• Can i vocalise everything in my IVR menus, instead of recording?

• I want to record some announcements with TTS. Is it possible?

• How many languages do you support?

• Can you make a TTS special for us with the voice that we choose?

• What is the succes ratio of this product?

• Do you give TTS services from the cloud?

• It can be hard for us to give a TTS service for our mobile apps, since it can also be used offline. Can we just put TTS in the app?

• What should we do when a new word comes into our lives or when we detect a word that TTS vocalises not so good?

• How much will i save if i buy TTS?

• How is the pricing of TTS?

• How many ports should i use if i have 50 ports of IVR?

• What resources do you need to use TTS?

• Does TTS work on virtual machines?

• How long does it take to implement a TTS?

• Which operating systems do you support?

• What should i do if i have questions or problems with TTS?

• What is Blacklist Identification?

• What is the size of a TTS product?

• Can TTS read abbreviations correctly? Can we define some custom reading rules in TTS?

• Can TTS decide how to read a word or a sign in a text correctly?

• Can TTS read in different accents?

• How does TTS work in Arabic?

• Is there a reporting tool for TTS?

• What are the license types of Verification on the Go (VotG) and Blacklist Identification?

• What are the license types of Vocal Passphrase and Password Reset?

• What are the license types of Forensic Voice Analysis?

• Can I define different reading rules for TTS?

• How is the TTS integration made with IVRs?

• How is the TTS cloud integration made?

• How is the TTS integration made with mobile apps?

• Can Arabic TTS read latin alphabet?

• Can Russian TTS read latin alphabet?

• Can I use TTS offline?

• Does TTS support high-available structure?

• Does VotG requires specific sentences during the call?

• Can VotG send alarms?

• Can we encrypt our archives?

• Do we have to create a voiceprint from single call only? What if call duration was not enough?

• Although the installation is completed and services are working, specific buttons doesn’t work on GUI. Why?

• What is Sestek AI?

• Where can I use Sestek AI?

• How is Sestek AI priced?

• How is Sestek AI’s licensing policy?

• Does Sestek AI work as on-premise? Or do I have to use Sestek’s cloud for Sestek AI?

• How many languages do you support for Sestek AI?

• Does Sestek AI run on virtual machines?

• Can I analyse the emotion of our customers?

• What should I do if I have questions or problems with Sestek Products?

• How is the application published for Windows operating system?

• What are the rules for versioning?

• Do you release a patch for fixes?

• Do you support Linux?

• Do you have Container support?

• Which Linux distribution do you support?

• Does SR and TTS have High Availability (HA) support?

• Do you require a load balancer on Genesys IVR?

• Which protocols does Sestek SR support?

• Which protocol should I use in order to use SR on IVR?

• What is the licensing model for MRCP?

• How does MRCP consume license?

• When does the IVR client open a channel to SR/TTS?

• Can I view the license use for SR/TTS?

• What is the difference between the Language model and the Grammar model?

• I would like to have license plate recognition on the application. Is that possible?

• I have speech recognition through dictation on my application. However, the numbers as a result of speech recognition are written out in letters, not in digits. Why?

• I have speech recognition through dictation on my application. The output of an ID number in the order of “XXXXXX10053” is put out as ‘’... ... ... one hundred fifty-three’’ in text. When I convert the output of this speech into digits, it turns out to be ‘’...153.’’ How can I solve this problem?

• How does the licensing process work in a distributed setup?

• Which languages do you support?

• We would like to use Sestek SR on our bank’s mobile application. Users might use contact lists that they created themselves during speech recognition on our application. What is your solution to this?

• Does this application have silent installation feature?

• Can your application be installed on a different directory?

• How is the Language Model created? Is it any similar to the SRGS Grammar?

• Does Sestek SR keep customer-specific data on application logs?

• What can be done to increase the success rate of speech recognition?

• What is VAD?

• Does Sestek SR have VAD? Do we need to use the VAD feature in our IVR?

• I use Sestek SR with IVR over MRCP. How would the Sestek SR react in case the current number of licenses I have is insufficient?

• I use Sestek SR over REST. How would the Sestek SR react in case the current number of licenses I have is insufficient?

• What can be done in order to increase the success rate of a speech recognition operation conducted in a noisy environment?