Accurate and efficient speech signal processing method for artificial intelligence
This technology is a pitch-synchronous signal processing method which can capture relevant speech information for artificial intelligence.
Unmet Need: Reliable processing method of raw speech signals
Many artificial intelligence systems rely on inputs in the form of raw speech signals which need to be converted into text for processing by the neural network. Traditional signal processing methods only crudely represent some speech features, losing valuable and important properties along the way. Newer approaches feed raw signal waveforms into large neural networks, but these methods can be computationally prohibitive and prone to noise and irregularity.
The Technology: Pitch-synchronized method for accurate and efficient speech processing
This technology is a pitch-synchronous speech processing method for artificial intelligence, separating waveforms into pitch periods and timbre vectors which more closely mimic human hearing patterns. These serve as more complete and accurate representations of speech compared to traditional methods, while being more concise and less noisy than using raw speech signals.
Applications:
- Artificial intelligence
- Speaker voice recognition
- Educational tool for language learning
- Accessibility tool for hearing impaired
Advantages:
- Mimics human hearing and speech processing
- Complete and concise representation of speech
- Less noisy
- More efficient and improved accuracy
Lead Inventor:
Related Publications:
Tech Ventures Reference:
IR CU22076
Licensing Contact: Dovina Qu