VoicePE (Voice Perceptual Evaluation)
The purpose of Voice-PE application (Voice - Perceptual Evaluation) is to serve as a teaching tool supporting the training in audio - perceptual evaluation, for current and future users of this form of qualitative characterization of the voice. It is based on a database of voice records that were made available after permission granted by the Ethics Committee of the Centro Hospitalar do Porto - Hospital de Santo António. Those voices were obtained in the context of hospital consultations in Portugal, and were classified by a panel of experts on audio-perceptual evaluation.
SingingStudio is an interactive and highly accurate software for the recording, analysis and representation of the singing, or spoken voice, on a scale of musical notes.
Some of the most relevant features of SingingStudio include:
- identification of the melody line in real-time,
- recognition of the melody line of the singing and transcription to the MIDI representation facilitating musical composition, and the conversion of the singing into an instrument sound such as oboe,
- ability to identify vibrato occurrences and to analyze and display the associated vibrato parameters (frequency in Hertz and extension in semitones),
- representation of the singing on a spectrogram where formants are identified and highlighted as well as occurrences of the singer’s formant,
- an innovative algorithm allowing to isolate the harmonic and noise components of the singing voice,
- flexible configuration of the analysis algorithms allowing, for example, to assess the impact of different analysis windows or the LPC order.
The VoiceStudio is a powerful signal processing and analysis software, specially devoted to the analysis and diagnosis of voice signals.
Some of the most relevant features of VoiceStudio include:
- acoustic analysis of voiced regions using well-established objective perturbation or quality parameters of the voice such as jitter, shimmer and HNR,
- a rich set of options for the graphical analysis of the voice, namely spectrum, spectrogram (narrowband and wideband), cepstrum, pitch marks,
- flexible spectrogram representation allowing for example to adjust color maps and their intensity, and to represent pitch over the spectrogram,
- an innovative algorithm allowing to isolate the harmonic and noise components of the voice signal,
- a user-friendly interface allowing for example to automatically identify and manually adjust, in an intuitive way, voiced regions of the voice signal.
Note: Available only in Portuguese.
MasterPitch is a fluency enhancer device designed to help speech therapists, voice professionals and stutterers to improve speech fluency. MasterPitch modifies the natural mouth-to-ear acoustic feedback such as to replicate the chorus effect which is observed when a stutterer sings in a chorus or speaks in unison with a second speaker. Under these circumstances stuttering is virtually eliminated or strongly reduced. MasterPitch modifies the acoustic feedback using Delayed Altered Feedback (DAF) and Frequency Altered Feedback (FAF). DAF modifies the delay of the natural acoustic feedback which can be adjusted between 40 milliseconds and 500 milliseconds. FAF modifies the pitch of the voice which can be adjusted between an octave below and an octave above, in intervals of 0.1 semitone.