Saving Steps With Single-Step Transcription

WRITTEN BY DAVIDE PETRAMALA

Saving Steps With Single-Step Transcription

In our fast-paced world, consumers are increasingly impatient. A whopping 90% rate an “immediate” response — 10 minutes or less — as either important or very important in a customer service setting. Additionally, 66% expect brands to understand their unique needs and expectations.

To lessen the burden on busy agents, contact center workers have begun adopting artificial intelligence (AI), voice AI, and real-time transcription services in earnest. These include legacy contact center platforms, contact center-as-a- service (CCaaS), Conversational AI platforms, and agent assist applications.

With an eye on making sure any agent can work productively and efficiently, one truly key area is real-time transcription.

Real-Time Single-Step Transcription is Critical

For many years, companies used offline transcription that typically occurred after the agents disconnected from the callers and functioned as recaps and learning experiences.

More recently, contact center leaders have adopted early versions of “real-time” transcription, but these offerings are still limited when it comes to their core capabilities.

These real-time single-step tools deliver faster, more accurate results for the agent…

First, these more basic versions tend not to offer authentic real-time processing, but instead use a multi-step, sequential process to handle text-to-speech and then utilize natural language processing (NLP). The result is that valuable time is lost, and the transcription can’t offer the meaning and understanding that the agent requires quickly enough.

But new next-gen offerings can collapse these distinct processes into a single step – recognizing speech through automatic speed recognition (ASR) – then creating meaning through natural language understanding (NLU).

These real-time single-step tools deliver faster, more accurate results for the agent and also allow voice assistants to go beyond mere sounds and words to better understand the meaning and even the intent of human speech.

What Does it Mean for the Agent?

This fast, sophisticated single-step process means that greater understanding is passed onto the agent “live” as they’re speaking to a customer.

The system not only generates the text of a conversation in real-time, but simultaneously structures it and tags key topics and entities from which it infers the speaker’s meaning and intentions.

This means that the transcription turns conversations into actionable opportunities, helping the agent to understand and better respond in the moment.

The real-time transcript also is easy to follow, thanks to the fact it’s formatted to include proper capitalization, punctuation, numbers, currency, dates, and more. Smart formatting and diarization are also combined to improve transcription usability with greater comprehension and accurate speaker identification—even during interruptions or when multiple speakers are in the same conversation.

Next Level Instruction

There is the option of combining single-step transcription with predictive analytics applications so that the agents can receive suggested responses and actions across a broad range of topics for guidance.

These topics are specific content that relate to common issues or concerns that a customer might contact a company about—and topics can be custom or pre-built.

For example, in a contact center agent assist application, if a customer tells the agent: “I’d like to ship this item back,” the single-step transaction tool will understand and automatically tag this as a request for a return/exchange. It can then retrieve this content and present it immediately to the agent, so they have specific, relevant responses without latency.

Other examples of available capabilities:

  • Caller says: “I’m on an annual plan and would like to change to monthly.”
  • System identifies relevant topic: Change of service.
  • Caller says: “I want to stop this service.”
  • System identifies relevant topic: Cancellation.
  • Caller says: “Call me back later tomorrow, on 555….”
  • System identifies relevant entities: Call back date and phone number.

Contact center agent assist topics might include:

Complaint topics:

  • Complaint
  • Service outage
  • Service not working
  • Service slow
  • Cancel service

Service topics:

  • Service appointment (install, repair, and others)
  • Add service
  • Renew service

Billing topics:

  • Billing error
  • Bill payment
  • Bill deferment
  • Refund

Return topics:

  • Returns (of products)
  • Unavailable (product)
  • Defective (product not working)
  • Damage
  • Repair (product)

Single-step transcription also helps establish meaning by offering a suite of features that can identify common entities like Social Security numbers, phone numbers, dates, time, and currencies.

Identifying entities is particularly useful with follow ups and line transfers. Imagine if a customer is transferred from one agent to another or a call drops and the customer calls again.

Because entities were tagged and also formatted properly (dates in 00/00/0000 format, Social Security #s as xxx-xx-xxxx), it’s easy and fast for the new agent to find specific information in the previous chat and quickly accommodate the customer. This helps with agent stress, efficiency, training, and customer service.

After the Call

In addition to helping agents and customers in the moment, single-step transcription transcribes the full customer journey – including pre-call exchanges with virtual agents – to supply high-quality transcripts for the purposes of analytics.

By analyzing these experiences post-call, businesses and agents can uncover the hidden signals within conversational data and become more informed about the pressure points affecting customer engagement.

These insights can ultimately fuel machine learning models and help them to adapt to specific and recurring customer issues within a particular business. These models continue to improve the more they are deployed.

…single-step transcription transcribes the full customer journey – including pre-call exchanges with virtual agents – to supply high-quality transcripts…

The service also provides next-level call management and compliance by enabling insights for 100% of calls as well as real-time auditing of the full customer journey – which is particularly critical for verticals like finance, healthcare, and government. Online gaming and betting call centers are also furnished with full transcripts to meet audit and compliance requirements.

Big Tech Limitations in the Call Center

While numerous software vendors have chosen a big tech vendor for their voice AI solution, many have been hampered by long deployment times and limited-to-no support—something that is unlikely to improve in light of these companies scaling back their voice technology offerings.

Voice AI isn’t a one-size-fits-all technology, and often requires a more customized strategy and technical implementation. Software call center vendors shouldn’t be left on their own to figure it out.

Independent voice AI vendors often bring years of experience and expertise that help software vendors get up to speed faster.

For instance, an independent vendor can deliver more turnkey transcription solutions by providing templates and blueprints for more repeatable use cases and solutions, such as appointment management, which includes setup, confirmation, and rescheduling.

Further, with a pure transcription offer the vendor takes on the entire NLU challenge of assigning meaning and identifying topics and entities. With independent voice AI experts, software vendors can get to market more swiftly with new use cases.

The Best Tool for a Well-Oiled Machine

A contact center can be a fast-paced and sometimes challenging environment, but leading vendors have endeavored to make single-step transcription a critical tool in supporting agents as they navigate conversations with customers.

No matter where you deploy —complex industries that require large vocabularies or in noisy settings with competing noise—this real-time single-step transcription will continue to function seamlessly as it introduces the next generation of transcription technology to any contact center environment.

Davide Petramala

Davide Piero Petramala is an experienced leader with over 20 years of experience building businesses and partnerships focused on customer experience. Since joining SoundHound, he has been focused on building a global eco-system of partners and customers to deliver enterprise voice AI solutions focused on both customer and employee engagement.