| Malaspina Labs advances the state of the art in speech enhancement. Malaspina Labs and its subsidiaries offer fully supported commercial implementations of our proprietary algorithms that improve the ability of both hearing impaired and non hearing-impaired persons to communicate more effectively in high-noise environments. Our focus is on the development of speech processing algorithms that operate deterministically in real-time within the resource constraints of milliwatt-class processors designed for embedded, medical and consumer devices. Active research areas include model-based synthetic reconstruction of human speech, model based discrimination of speech-of-interest from competing background speech, and efficient encoding of speech information for extremely low-bandwidth digital communication.|
Malaspina’s VoiceBoost™ signal processing blocks go beyond traditional filter-based noise reduction approaches by employing a mathematical model of the human voice to allow the detection, discrimination and isolation of speech-of-interest from high-volume competing background noise, including high volume babble speech and impulse noise.
Malaspina’s VoiceBoost™ software is rotation & orientation robust and is effective in enhancing speech within near-field and arms-length audio signals from single omni-directional microphones or directional microphones, as well as spatially separated input signals from multiple microphones.
- Configurations with as little as 8 msec latency and under 5 MIPS CPU
- Available in source code or binary form for integration into existing audio processing pipelines
- Increase speech intelligibility by hearing impaired users in noisy environments
- Iincrease automatic speech recognition performance and mobile voice call quality in noisy environments
VoiceBoost is available for Synopsys DesignWare® ARC® 600 and ARC 700 series architectures.
Learn more about how Malaspina Labs and Synopsys work together.