Synthesizing Voice Through Cloud-Based Innovation
Find The Voice
Create The Script
Access Cloud Recording
=
Crystal’s Syntheiszed Voice Powered By AI
Who Is Crystal?
The augmented intelligence company iGenius developed Crystal, a virtual advisor for data intelligence, enabling more business people to make smarter, faster decisions assisted by AI. Crystal changes the user experience in data and analytics: it is one tool that connects multiple data sources and lets users ask the questions they need answers to in true natural language, as if talking to a colleague.
Crystal reduces the time users spend on exploring data, while giving them more time to act on the most relevant insights. This increases autonomy, enrichment, and augmentation of how decisions are made at every level of the organization and impacts operational eciency and revenue growth. In order to develop and offer a unique and customized synthetic voice for Crystal, iGenius came to TransPerfect’s AI data solutions division, DataForce, and audio/video division, MediaNEXT
Overcoming Obstacles Through Innovation
The project kicked off at the height of the pandemic—studios were closed, voice talent were stuck at home, and the media industry ground to a halt. iGenius needed to record Crystal's voice but their options were limited. They turned to TransPerfect for our hybrid, cloud-based recording solution: StudioNEXT. Using this platform, the talent was able to record in the comfort of her own home, avoiding the need to commute to a studio, touch equipment, and come in contact with others. The teams were able to create the synthetic voice of Crystal entirely through this internal cloud-based technology, tailoring and producing it to match iGenius's specific project requirements.
Building The Voice
To develop Crystal’s voice, we needed to train the text-to-speech engine on a series of recordings from the voice actor. These recordings were eventually fed into an AI model, which essentially learned a probabilistic model of a spoken language, treating each sentence as a sequence of sounds. We then created an algorithm to filter a standard corpus from corpus linguistics to create Crystal’s voice. The seamless integration of both the actual voice and AI technologies was accomplished entirely with internal software and in a remote environment.
"
For our team, it's really important to listen to the client and understand their requirements, do our own research, to understand the space that they're working in and meet, and if possible exceed their expectations for us. It was a really great experience to be able to work with both DataForce and MediaNEXT and find a solution that satisfied the client all in all for us.
Fred Bane, Data Scientist TransPerfect
"
• • • • Bridging Text & Speech • • • •
STEP 1 — THE VOICE
For a virtual advisor, the voice is the face of the brand. Although Crystal had no physical features, the sound of her voice alone needed to create a specific feel, atmosphere, and lasting first impression. To create a synthetic voice, we turned to MediaNEXT’s and DataForce’s vast database of linguists and phoneticians, and iGenius cast samples of different voice talents and styles. With multiple options, inflections, and mannerisms in mind, iGenius was able to identify who they wanted Crystal to be.
STEP 2 — THE SCRIPT
DataForce and iGenius worked together to identify the overall length of the script, the number of sentences, the speaking duration of each sentence, and, most importantly, a particular balance of phonemes in the corpus, which matched the overall distribution of English phonemes.
STEP 3 — THE RECORDING
Working with Jennifer, the voice of Crystal, we brought the script to life through StudioNEXT in a fully remote environment. Using her cloud recording kit, Jennifer could log in and out without having to remember where she left off —everything was uploaded to the cloud. Having never done anything like this before and dealing with noisy construction in her building, Jennifer was able to move her devices to a quiet location and complete the project with ease.
"
The main focus for the research department at iGenius was to create a synthetic and customized voice for our main product, Crystal. Through my LinkedIn connection Sofia Silva, account executive for DataForce by TransPerfect, we managed to bring this idea to reality. Working together with DataForce and MediaNEXT gave us the confidence to create a large data set of phonetically balanced sentences and corresponding high quality audio clips to be able to train a high performance AI model with text-to-speech capabilities.
Marco Bocchio, PHD Machine Learning & Data Science Team Lead iGenius
"
The Result
iGenius was looking for a voice to enhance data exploration, analytics, and the overall experience for their clients. With Crystal, they provide a synthetic human voice for their clients to engage with in a natural way, as if it were a colleague. Working together, iGenius, DataForce, and MediaNEXT collaborated to bring the idea of a synthetic voice to reality through a customized, hybrid solution.
DataForce has a global community of over 1,000,000 members from around the globe and linguistic experts in over 250 languages. DataForce is its own platform but can also use client or third-party tools. This way, your data is always under control.