About

An intelligent audio recorder for the iPhone! MoJo-mate opens up a whole new perspective on sound measurements, by performing semantic audio analysis.

• Overview
The application provides long-term audio analysis capabilities, based on semantic audio processing concepts. Intelligent Sound Analysis brings real time audio-pattern recognition, visually resulting into an event detection markup timeline. A dynamic audio-samples database is used as a pattern-storing matrix, which is configurable by users. Α build-in audio semantic engine is capable of detecting audio events and patterns.

• Highlights
– Perfectly polished UI, delivering professional-grade user experience
– State-of-the-art implementations for Audio Feature Extraction
– Temporal Feature Integration and Pattern Classification algorithms
– Calibrated using reference equipment

• Under the hood
– 44.1kHz/32bit raw audio recording
– 20Hz to 20kHz frequency response
– 90dB dynamic range, from 25dB to 115dB SPL[A]
– ±1.4dB accuracy @25dB-115dB SPL[A]
– Low latency and processing-loss spectral analyzer
– Audio I/O latencies monitoring and compensation
– Build-in audio feature extraction engine for estimating temporal an spectral audio features
– MFCCs, ZCR, Spectral Centroid, Spread, Flatness, Crest Factor and Rolloff calculation
– 1NN and Euclidian-Distance based classifiers that enable audio pattern classification
– Enhanced temporal feature integration for improving detection robustness

• Audio Semantic Analysis
– Audio event detection and pattern matching annotation
– Option for capturing new audio samples and building a custom audio pattern library
– Option for choosing a subset of all available patterns on each measurement
– 1NN and Euclidian-Distance based algorithm as choices for classification
– Mean, Variance and MeanVar models as choices for temporal feature integration
– Audio event detection sensitivity adjustment
– Audio pattern matching sensitivity adjustment
– Audio features selection support

• Advanced Calibration
– Calibrated and equalized for each iPhone model
– Calibrated for the MicW i436, as an external input source
– Calibration data is OTA (Over the Air) updated
– Independent equalization banks for both embedded microphone and external input
– Custom octave-based gain adjustment support

• Session Management
– Frame-based time-series of measurement data handling
– Overall statistics calculation for noise measurements
– Event detection timeline annotation for long-term monitoring
– Photo capture capability
– Time and geolocation awareness support
– Title, location and comments metadata support
– Audio recording (CAF format) and measurement data (CSV format) export capabilities

• Additional Capabilities
– Option for keeping the device awake during recording
– Option for auto-stopping measurements after a pre-configured duration
– Background recording capability
– Upside down orientation support