VoicePrinter vs EyeSound Vocal

Sound is decomposed into two dimensions and displayed continuously over time. The premium version offers a new style of audio recorder/player. This app can be used for analysis of Human voice, Environmental sound, Sound of animals, musics, etc. The specifications are as follows. Sampling rate = 10000 to 44100 Hz Display maximum frequency = 1000 to 22050 Hz Display time range = 2 to 10 seconds Frequency axis display resolution = 100 Time axis display resolution = 10 / sec From version 1.1, recording, playback, import, and export functions based on sound and voiceprints can be used by in-app purchase. In this case, banners will not be displayed. The premium version allows recording, playback, import of external sound source files, and external output. ・Record under the following conditions Sampling frequency = 10000~44100Hz ・Display audio analysis results under the following conditions (audio is played in sync with the analysis screen) Maximum display frequency (high-pitched display frequency limit) = 1000~22050Hz (half the sampling frequency or less) Display time range (time that can be displayed on one screen) = 2~10 seconds Frequency display resolution (frequency axis: number of data displayed on the vertical axis) = 200 points Time axis display resolution (time axis: display interval (pitch) on the horizontal axis) = 50~200ms (10~200 points) ・Importing external audio source files Imports 16-bit linear PCM mono audio sources. (In the case of stereo, only 1ch is imported.) ・External output Outputs as 16-bit linear PCM mono. *To input and output data to iCloud Drive, you must enable iCloud Drive in System Preferences. *******

EyeSound Vocal converts spoken words and other sounds into data rich images. These are seen in an active spectrogram displayed on the screen of your device. Latency of sound-to-image is less than 100 milliseconds. The spectrogram can be tuned by the user so that images of most spoken words are recognizable and are unique. If one has memorized a good sized vocabulary of word images, there can be some visual comprehension of spoken conversations just from viewing the app's spectrogram. Details in the spectrograms indicate inflection and volume. Applications/uses: - entertainment - watch as sounds and conversations morph into image streams - art - create and download spectrogram images that correspond to spoken phrases or other sounds ------------------------------------------------ NOTE: EyeSound Vocal does not capture medical data and does not provide health related measurements, diagnoses or treatment advice. It is not intended for use as a tool for treatment of medical conditions. It is not intended for use as a tool for scientific measurements. ------------------------------------------------ User adjustable parameters in the app include the rate at which sonogram images progress across the screen, resolution, colors, color switching and color mapping to sound intensity, high frequency boost. Features include auto gain, display of saved images next to active or paused spectrogram, pause/resume for capture of images, save/recall of images, save/recall of setup parameters, default parameter setup that is well suited to the visualization of human speech. full screen mode for a view of nothing but the active, or paused, spectrogram. How the app works: Sound is captured by your device's microphone. The app processes the sound data in small sized packets. For each packet the app computes frequencies and intensities. A spectrogram is created by color mapping intensities across frequency bins and then plotting these versus time. With ongoing plotting of packet data as it arrives the spectrogram becomes 'active' - it appears as a movie. EyeSound - Past, Present, Future: 45 years ago, in 1979, a young chemical engineer fresh out of MIT had just begun working for GE in Niskayuna, NY. In his spare time he built and experimented with breadboarded circuits that incorporated resistors and capacitors, transistors and ICs and lights, microphones and speakers. One day he assembled a device consisting of a row of LEDs tied into a circuit that would sequentially light the LEDs in accordance with an input voltage signal. When he manually swept this device in an arc he saw - very much to his surprise and to his fascination - images of complex waveforms painted across empty air. This simple device was giving a glimpse of all of the information that was normally only heard! The engineer had found a mission: improve upon the device to open to the world a whole new dimension of visual perception. A team of 2 of us - the engineer and the coder - have over the past several months turned the concept into an app. The initial release is happening now. The 45 year old mission is on the verge of realization. We anticipate releasing new versions of the EyeSound Vocal app on a regular basis. Users - please send us your suggestions and we'll use them as direction for improvements and use them to expand on our user tips. We will be taking a look into interfacing EyeSound with two types of peripheral devices (1) AR glasses which could put the active spectrogram front and center in your field of view - so that while viewing the spectrogram you will be more in the same world with the people around you; (2) wearable, directional and better quality microphones to avoid the pick up of background sounds that at times obscure the visualizations.