CHALLENGES
The Client’s devices struggled with picking up strong accents and varied tones and pitches when transcribing speech.
Tests were conducted to determine what was needed to improve the Client’s voice-recognition software and to help it recognize different accents, tones and pitches for greater accuracy.
SOLUTIONS
Qualitest provided a full suite of AI Data Services including data collection, ingestion, and automated and manual tagging.
We helped the Client initiate, create and deliver on a variety of data collection initiatives to improve their speech recognition software.
RESULTS
Qualitest delivered statistically significant results in all phases of the program of work undertaken for our Client.
The program included promoting the collection to potential participants, signing people up, and conducting sessions in which the utterances were captured. It was replicated internationally and for other teams within the Client’s organization who had similar data-collection needs.
Since our Client’s inception, they have changed the way people connect and operate a global social media platform and digital advertising enterprise. Their apps empower millions around the world, and they are now moving beyond 2D screens towards immersive experiences such as augmented and virtual reality to help build the next evolution in social technology.
They are continually building innovative new ways to help people feel closer to each other, and the make-up of their organization reflects the diverse perspectives of the people who use their technologies.
Already lagging behind with the introduction of other smart-hub devices, the Client understood that its success relied upon targeting a narrow set of features for multiple devices (specifically, calling) and gathering a large and diverse set of speech utterance data to ensure that the device would recognize and respond accurately when prompted.
Early testing and data confirmed that the device was struggling with strong accents and varied tones or pitches. The Client needed more data to build the patches necessary to improve its voice-recognition software. To capture these speech tones and patterns management decided to leverage its diverse employee population to “dogfood” the technology for capturing speech tones and patterns.
With the product launch just months out from the start of data collection, the Client was compelled to short-list vendors who could mobilize teams across the country to deliver a “first-in-kind” data collection program within a very short timeframe. Qualitest quickly rose to the top of the list.
Qualitest provides a full suite of AI Data Services, including data collection, ingestion, and automated and manual tagging to create algorithm-ready quality data optimized for artificial intelligence (AI) and machine learning (ML). The Client’s complete methodology initiates, creates, and delivers on a variety of data collection initiatives for areas such as speech, humans, and spaces.
With our expertise in speech data capture, such as accents, dialects, speech patterns, cadence, and other speech nuances and behaviors, Qualitest was able to quickly scope out and deliver the teams necessary to target the company’s preferred employee locations across the country. Qualitest partnered with the Client to develop a strategy and deploy the mobile teams, staffed with leads and moderators, to conduct test sessions with the company’s full-time employees.
The biggest challenge of this project was enrolling participants. To create interest, the project team developed a multi-faceted marketing program that included internal social media promotion, free swag, targeted flyer placement, and live interaction with employees during high traffic mealtimes. Once employees had signed-up to “dogfood,” Qualitest fine-tuned its communication strategy to ensure leads would honor their commitment and show up for their scheduled sessions.
The team used a “help-chat” model to engage and remind employees of available time slots. Proactively working with internal stakeholders from the engineering team, Qualitest was able to implement several innovative program efficiencies. Cross-training test session teams on best-practices and establishing a steady cadence of reporting allowed for optimal knowledge collection and sharing between offices, ensuring Client visibility and engagement throughout the project.
Download the PDF
