Toxic conversations between players is a widespread issue in the online gaming world. One of the largest developers of multiplayer online games turned to Google and Pythian for assistance with a solution for detecting toxicity in gameplay conversations by analyzing the audio stream.
The company has existing toxicity detection models that work well with instant messaging chats. However, they wanted to expand those chat detection models into online speech conversations. Pythian developed a prototype solution.
What we did
Leveraged a combination of Google Speech to Text API and Tensorflow to build a gameplay transcription and toxicity detection prototype
Optimized recognition of gaming slang
Leveraged transfer learning on the publicly available toxicity content and gaming slang
Technologies used
Google Cloud Platform
Google Text to Speech API
Google Cloud Storage
Google Kubernetes Engine
Google Cloud Memorystore
Google StackDriver
TensorFlow
Key Outcomes
The company can now expand its natural language toxicity detection capabilities into audio gameplay conversations.