NovoSpeech

The Speech Recognition Challenge: Speech is one of the most intuitive means by which we interact with our surroundings. Automatic speech recognition (ASR) is a complex technology that aspires to allow humans to interface with machines in this most natural of modalities. Yet, despite great advances in ASR, the user experience with ASR-based interfaces in real-life environments is still not good enough for speech recognition to be embraced by the mass market. In fact, analysts believe that ASR, despite its potential as a killer app, has achieved only 15-20% of its market potential. The NovoSpeech Technology Re-inventing Speech Recognition: NovoSpeech has analyzed the bottlenecks inherent to existing speech recognition solutions and re-examined the approaches that were being applied in the past. This meticulous, out-of-the-box thinking has led us to introduce proprietary changes deep within the speech recognition engine resulting in a robust, speaker-independent, on-device, continuous speech recognition technology with superior accuracy rates. The NovoSpeech Advantages: -Highly noise-robust recognition accuracy: Unprecedented accuracy even in real-life (noisy) environments. Benchmarking results show a game-changing 35% improvement in NovoSpeechs accuracy as compared to state-of-the-art ASR. -Dramatic reduction of computational complexity: NovoSpeech deploys large-vocabulary continuous speech entirely on the mobile device, eliminating the constraint of current ASR mobile solutions that must be connected to the cloud. -Speaker-independent: Accurate identification of words regardless of gender, accent, or speaking style.