Government contact centres deliver essential services to millions of people in their local region, city or state. In the UK, services such as HMRC, Jobcentre Plus, the Driver and Vehicle Licensing Agency, Department for Work and Pensions etc, receive collectively over 100 million calls per year.
The challenges faced by these contact centres are the challenges faced by the world—they are social, financial, unpredictable, fast-changing, and highly demanding.
Contact centres must therefore be able to deliver critical services at scale, while facing additional pressures to operate efficiently, reduce risks from fraud, and protect staff from undue stress.
Intelligent data, technology, artificial intelligence (AI) and machine learning (ML) have contributed to lighten the burden.
The latest technologies from Intelligent Voice (IV) can be applied across diverse government contact centres across the world to provide effective data capture and reporting solutions. These IV technologies help reveal knowledge that improve service quality, resource management, reduce fraud risk, provide healthier work environments, and more effectively manage increased customer demand.
Recording conversations and converting them to text is only the first step in realising the value of audio content. IV’s modern analytic techniques operate on the output from Automated Speech Recognition (ASR) to unveil important trends, patterns, and themes that were previously hidden.
IV’s ASR offers an evolution to standard speech-to-text solutions. The solution is created for how people speak rather than how they type. IV’s SmartTranscript solution can identify topics discussed in a conversation and find alerts for specified keywords.
Calls can be prioritised for further review through clickable links within the transcript that navigate to the related parts of audio.
The audio review player incorporates the audio file, linked or embedded, with a navigable time-bar waveform, playback rate slider, and jump back and forward controls. Ongoing research work means that more and more dialects and accents can be detected over time, and the system can operate in over 25 languages and dialects, automatically selecting the best one for every call.
IV’s Graphics Processing Unit (GPU) accelerated ASR and SmartTranscript solution, which builds on ASR, provides assessments of selected audio at scale and speed. The SmartTranscript solution is extremely effective in improving operational efficiency and enables government contact centres to be more productive and make better-informed decisions.
Using its hyper-accelerated speech recognition algorithms, IV can speed through thousands of hours of telephone/virtual calls and video in no time.
It then uses a blend of Natural Language Technology and sophisticated search to help pinpoint calls that should be listened to, which allows better targeting and quicker accurate review.
It reviews recordings through pre-highlighting of transcribed text via patented Natural Language Processing (NLP) for speech, as well as listening to a human voice, thereby rapidly assessing mission-intelligence and value in a call.
The system can easily be tuned to adapt to words or phrases that are of particular interest. It presents the spelling of the most likely language of the most likely spoken word while retaining a full index in all processed languages for search purposes.
There may be multiple reasons for contact in a single conversation between a citizen and a government contact centre adviser; most of those reasons are valuable and important and some less so can be fraudulent.
Intelligent Voice’s latest LexiQal product provides unique Conversational Analytics that identifies behavioural characteristics of speakers in recorded speech, tuned to the output from ASR. The analysis provides insights into the speaker’s credibility, emotional state or behavioural changes that are significant in context. LexiQal can also measure caller sentiment (positive, netural, negative) at utterance level with a high degree of accuracy, unique to IV.
Conversational analytics works by detecting patterns in speech via a series of markers, and the time-based proximity of these indicators being triggered. LexiQal has a decision engine, that makes recommendations to the administrators regarding calls/recordings of interest.
LexiQal’s scoring method of the markers (Emotional Recognition) uses linguistic analysis only to determine the likely behaviour of interest, whether of the caller or the call handler, or both. The technology automatically identifies these conversational features, weighs their significance, and makes recommendations. The insights are valuable across both sides of the call, agent and caller alike, with recommendations used to ‘inform’ human-made decisions to act or not.
Scenarios or call-types where this technology can be applied include: