Nuance Recognizer as a Service overview

Feature coming soon

Prerequisites 
  • Genesys Cloud CX 2 or Genesys Cloud CX 3 license
  • Integrations > Integrations > Add, Delete, Edit, View permission
  • Architect > Grammar > Add, Delete, Edit, View permissions

Transactional IVR applications often need a multi-digit or numeric input. In addition to DTMF, your customers increasingly work in hands-free environments. As such, you must capture the information that you need via automated speech recognition (ASR). When you add ASR support for customer input, reuse custom and fine-tuned grxml grammars from previous implementations, and combine them with bot capabilities, you can create a wider suite of ASR applications.

Nuance Recognizer

Nuance Recognizer understands and interprets spoken and touchtone input to help deliver seamless self-service. The underlying recognition engine is grammar-based, which means it requires grammars to interpret a caller’s utterance.

Constrained grammar recognition engines are especially useful for:

  • Recognizing alphanumeric inputs such as account numbers and tracking numbers.
  • Small scoped applications that are designed for interactions with a small set of words and phrases to recognize.
  • Directed dialog to assist in navigating a menu tree of items, either used for the first interaction of a caller, or as the basis of the system’s conversational design.

The gRPC protocol allows a client application to request speech recognition in all the programming languages supported by gRPC.

gRPC is an open source RPC (remote procedure call) software used to create services. It uses HTTP/2 for transport and Protocol Buffers version 3 (“proto3”) to define the structure of the application.

Nuance Recognizer as a Service integration

When you install the Nuance Recognizer as a Service integration in Genesys Cloud, you can use a traditional, grammar-based ASR in your Genesys Dialog Engine Bot Flows. This implementation provides you with a simple, directed dialog speech application if you do not need natural language understanding and do not want to train and maintain it. A traditional, grammar-based ASR gives you higher accuracy for constrained domains and tighter control over the grammar tuning, and is easy to implement and tune. The integration increases the number of options available in terms of languages and voices in your customer interactions. 

Add the grammar-based Nuance Recognizer as a Service integration and then choose from Nuance voice and language options in the Ask for Slot action in Genesys Dialog Engine Bot Flows actions in Architect:

For more information, see Create a bot flow and use third-party ASR grammar quick start guide.