voice analysis
voice analysis in sessions: acoustic signals and limits
Audio contains features that do not appear in a transcript, such as rhythm, pauses and turn-taking. nexmin’s voice analysis presents some of these signals with time references so you can listen to them in context.
signals analysed
The analysis can show estimates of prosody, expressive variation, speech rate, pauses, response latency and turn-taking. These are indicative computational outputs; they are not clinical measurements and do not describe a person’s experience on their own.
how to review the signals
Each signal can help you locate an audio segment and listen to it alongside the transcript. A pause, a change in pace or a difference between voice and words can have several interpretations; the output does not determine what is happening in a session.
what the analysis can and cannot conclude
The analysis presents acoustic features; it does not identify an emotion or establish what a person feels. Review each result against the audio and session context. Voice labels are assigned for each session and may need correction.
alongside the rest of the analysis.
The voice does not stand alone: its signals feed into process reading by Pensa and sit alongside process variables and the analysis configured for your practice. You can compare those observations with the session content.
frequently asked questions.
Is this emotion recognition?
No. The feature presents acoustic signals such as rhythm or pauses; it does not determine what emotion a person feels. Review results against the audio and session context.
How reliable are these measures?
They are computational estimates meant to guide your listening, not a clinical measurement instrument. Each signal includes its minute so you can check it against the real audio.
Is my voice, or my consultants’ voices, stored as an identifier?
Voice labels help distinguish turns within a session and may need correction. See the privacy policy for information about audio processing and retention.
see which signals voice analysis provides.
14 days free, no card