Serving technology enthusiasts for over 25 Years. TechSpot is a source of trusted tech advice and analysis.
Teleperformance SE is the world’s biggest call center operator and has implemented an artificial intelligence system to soften accents of English speaking Indian workers in real time. The company claims that this technology will
Enhance customer satisfaction and understanding. Thomas Mackenbrock, Deputy Chief Executive Officer at the company, told Bloomberg that
“When you have an Indian agent on the line, sometimes it’s hard to hear, to understand,” . “[This technology can] neutralize the accent of the Indian speaker with zero latency, [creates] more intimacy, increases the customer satisfaction, and reduces the average handling time.”
This technology analyzes and modifies the speech input to match a specified Accent while preserving speaker’s original Voice and Emotion. Speech recognition is used to capture the speaker’s voice in real time. Advanced algorithms then translate the spoken words to text, taking into account accents and speech patterns. After the system has transcribed the speech, it analyzes the speaker’s accent and pronunciation patterns. It then applies AI models that have been trained on datasets with different accents to modify voice.
The software modifies intonation and stress patterns as well as phoneme pronunciation during the conversion to align with the desired accent. The system uses text-to-speech technology to synthesize and convert the phonetic pattern into a synthesized speech that maintains the original tone, emotion and identity of the speaker.
Teleperformance deploys technology with background noise cancelation in Indian call centres, providing customer service for international clients. Customers include Apple, TikTok and Samsung Electronics.
This software is being developed as the call center industry is facing challenges due to the rise of AI chatbots. Teleperformance’s share price dropped significantly last year after the Swedish fintech firm Klarna Bank revealed that its AI assistant could perform the equivalent of 700 full-time agents. Teleperformance’s response was to use AI to enhance its workforce of over 490,000 workers, rather than replace them.
Sanas claims that its goal is “accent-based discrimination.” While the software may not directly replace workers, there are concerns over the potential impact of the software on call centers like those in the Philippines, who have built their market positions on high-quality English speakers. The software currently supports Indian and Filipino accents. Sanas is working on versions for Latin America and other regions. Mackenbrock said that AI will be ubiquitous “the human element will be incredibly important” for building connections and improving customer experiences.
