...
The following table describes Mental Fitness vocal biomarker voice features. Sonde APIs will return the scores for these features. Both the recommended end user-friendly and expanded explanation descriptions are provided. Sonde Mental Fitness Tracker App showcases a recommended implementation of how to share feature descriptions and score interpretations with mobile app end users.
MF Acoustic Scores - Version
...
5 (Current App SDK version)
The following scores are available through the API (Use Case document )
Acoustic score definitions and range interpretation (this section for app developer reference)
Note: if any of the scores are beyond the specified min-max range (see measure/ display range in table), the scores are clipped to a minimum or maximum values.
Each acoustic and aggregate vocal biomarker listed below is correlated to mental fitness: higher values indicate higher mental fitness, lower values indicate lower mental fitness (except pause duration, which is opposite).
Please note -
Mapping of the voice feature sub-score ranges to labels we do not provide such labels as there are no external (non-Sonde, validated, peer-reviewed, published) sources to support this approach.
Additionally, we have not correlated individual feature values directly to clinical reference data on mental health.
MF Acoustic Vocal biomarker scores available through API
| Unit For display in app | Approximate reference range 25 - 75th percentile of population distribution | Measure / display range API backend will clip values outside this range | Remarks | Direction for a higher Mental Fitness |
---|---|---|---|---|---|
Smoothness | % | 90 - 95% | 88 - 100% | Regularity of voice pitch periods | Increasing |
Control | % | 80 - 90% | 78 - 93% | Regularity of voice pitch amplitude | Increasing |
Liveliness | octaves | 0.15 - 0.30 octaves | 0 - 0.45 octaves | Range of vocal pitch used while speaking (one octave is a doubling of pitch) | Increasing |
Energy range | dB | 5 - 10 dB | 3 - 12 dB | Range of vocal intensity used while speaking (10 dB sounds twice as loud) | Increasing |
Clarity | kHz2 | 0.30 - 0.45 kHz2 | 0.20 - 1.20 kHz2 | Range of sounds made while speaking by changing the shape of tongue, mouth and throat | Increasing |
Crispness | ms | 200 - 300 msec | 100 - 400 msec | Average time of single speech sounds measured from beginning to end of vocal cord vibration | Increasing |
Speech rate | words/min | 75 - 125 words/ min | 25 - 220 words/ min | Number of words spoken per minute | Increasing |
Pause duration | sec | 0.25 - 0.60 sec | 0.1 - 1.0 sec | Average duration of pauses between speech sounds (higher values imply lower mental fitness) | Decreasing |
MF Acoustic Vocal Biomarker Mental Fitness Score through API
| Unit For display in app | Approximate reference range 25 - 75th percentile of population distribution | Measure / display range API backend will clip values outside this range | Remarks |
---|---|---|---|---|
Mental Fitness Score | % | 72 - 81 | 0 - 100 | 0-69: “Pay attention” |
MF Acoustic score interpretation (recommended descriptions for user explanation in-app)
Vocal biomarker | Brief Description Directly below score display | Expanded Description Below score history / trend chart |
---|---|---|
Smoothness | Reduced mental health can negatively impact our ability to have precise control over vocal pitch. When vocal pitch control decreases, the smoothness of our voice decreases. | This metric measures small variations in voice pitch that occur naturally when we speak. Pitch refers to the highness or lowness of our voice, and we use it to emphasize words and convey emotions. However, small and rapid irregularities in pitch can also occur. If we have less control over our voice, it can lead to a hoarse or rough quality. Typically, smoothness of the voice falls between 90-95%. This degree of control over our vocal muscles is essential for speaking, and changes in muscle tone, fatigue, inflammation, and mental health can affect it. In particular, changes in mental health can be reflected in changes in smoothness. |
Control | Reduced mental health can negatively impact our ability to have precise control over vocal muscles. When vocal muscles control decreases, our control decreases. | This metric measures small changes in pressure in the sound waves that our vocal cords create while we speak. If we have reduced control over our voice, these pressure variations can increase, which may lead to a breathy quality in our voice. Typically, our degree of control over voice production will fall between 80-90%. Speaking requires rapid and precise control over our vocal muscles, and changes in muscle tone, fatigue, inflammation, and mental health can all affect this degree of control. Specifically, changes in mental health can result in changes in our ability to control our voice. |
Liveliness | Depressed emotions or reduced mental fitness can affect how much vocal variety we use. Less variety or liveliness in our voice results in a more monotone and less engaging voice. | This metric measures the intentional changes in voice pitch that occur when we speak. Pitch refers to the highness or lowness of our voice, and we use it to emphasize words and convey emotions. A higher liveliness score indicates a greater range of pitch variation, which can make our speech more engaging. Typically, this measure will fall between 0.15-0.30 octaves (an octave is a doubling of pitch). Using vocal variety is essential for engaging listeners and expressing emotions while speaking. However, when emotions or mental health are affected, liveliness can decrease, resulting in a more monotone and less engaging voice. |
Energy range | Depressed emotions or reduced mental fitness can cause our vocal energy range to decrease. When we feel at our best, we speak with a varying intensity for emphasis, leading to higher energy range. | This metric measures the variations in vocal energy while speaking. Energy range is influenced by how much effort we put into making speech sounds, so louder voices tend to have more energy than softer voices. The energy of sound is measured in decibels (dB), and the energy range measures the extent to which energy changes while speaking. Typically, this measure will fall between 5-10 dB (10 dB is a doubling of loudness). Vocal intensity plays a crucial role in emphasizing words and engaging listeners while speaking. However, when we are disengaged, tired, or experiencing reduced mental health, our energy range can decrease, resulting in a less engaging and less impactful voice. |
Clarity | Reduced mental fitness can result in reduced movements of the tongue, jaw and lips, reducing the range of sounds we produce. This can lead to lower vocal clarity. | This metric measures the range of difference when producing different speech sounds. We do this by altering the position of the tongue, jaw, and lips. The more pronounced these position changes are, the more distinct the speech sounds become, resulting in increased clarity and more intelligible speech. Typically, this measure will fall between 0.30-0.45 kHz². Speaking with clarity requires rapid and pronounced adjustments of the tongue, jaw, and lips. Reduced movements can result in lower vocal clarity, which can be associated with reduced mental health. |
Crispness | Reduced mental fitness can lead to reduced effort at producing speech, leading to shorter durations of each sound. This can result in a less crisp sounding speech. | This metric measures the average duration of vowel sounds in speech. Holding a sound steady over time requires coordinated and effortful use of the vocal tract muscles, which can be impacted by mental health or fatigue. Measuring crispness makes changes in speech sound durations visible. Crispness is measured in milliseconds (ms) and will typically fall between 200-300 ms. When we speak, each sound we produce has a typical duration. Fatigue or reduced mental health can lead to shorter sound durations and less crispness. By measuring changes in vowel durations, we gain insights into one's mental fitness. |
Speech Rate | Reduced mental fitness can slow us down, including how we speak. Changes in speech rate can indicate changes in mental fitness. | This measures the rate at which we speak, represented by the number of words spoken per minute. Alertness, fatigue, medications, and mental health can all influence the rate at which we speak, typically between 75-125 words per minute. Changes in mental health can be observed through changes in speech rate. |
Pause duration | If we are not feeling well we tend to need more time to think about what we say or do. Measuring the average time of silence gaps in speech can indicate changes in mental fitness. | This measures the average duration of the silent gaps we make when we speak. Longer pauses can indicate difficulty in finding the right words and constructing coherent sentences, which can be caused by reduced mental health or fatigue. Measuring pause duration reveals how often our thought processes slow down. Pause duration is measured in seconds (sec) and typically falls between 0.25-0.60 seconds. |
MF Aggregate score interpretation (recommended descriptions for user explanation in-app)
Vocal biomarker Aggregate score | Brief Description Directly below score display | Expanded Description Below score history / trend chart |
---|
Vocal biomarker Aggregate score | Brief Description Directly below score display | Expanded Description Below score history / trend chart |
---|---|---|
Score (Aggregate) | Your mental fitness score is determined by analyzing specific vocal features that have been demonstrated through research to have a relationship with mental fitness. By monitoring changes in your score over time, you can reflect on how your mental fitness may be evolving. The score ranges (pay attention, good, excellent) provide a helpful context for interpreting your results relative to a broad range of users. It is important to note, however, that these scores are not a substitute for medical evaluations and should be viewed as only one aspect of understanding your overall health and wellness. | n/a |
MF Acoustic Scores - Version 4 (Current API version)
The following scores are available through the API (Use Case document )
...
Each acoustic and aggregate vocal biomarker listed below is correlated to mental fitness: higher values indicate higher mental fitness, lower values indicate lower mental fitness (except pause duration, which is opposite).
Please note -
Mapping of the voice feature sub-score ranges to labels we do not provide such labels as there are no external (non-Sonde, validated, peer-reviewed, published) sources to support this approach.
Additionally, we have not correlated individual feature values directly to clinical reference data on mental health.
MF Acoustic Vocal biomarker scores available through API
| Unit For display in app | Approximate reference range 25 - 75th percentile of population distribution | Measure / display range API backend will clip values outside this range | Remarks | Direction for a higher Mental Fitness |
---|---|---|---|---|---|
Smoothness | % | 90 - 95% | 88 - 100% | Regularity of voice pitch periods | Increasing |
Control | % | 80 - 90% | 78 - 93% | Regularity of voice pitch amplitude | Increasing |
Liveliness | octaves | 0.15 - 0.30 octaves | 0 - 0.45 octaves | Range of vocal pitch used while speaking (one octave is a doubling of pitch) | Increasing |
Energy range | dB | 5 - 10 dB | 3 - 12 dB | Range of vocal intensity used while speaking (10 dB sounds twice as loud) | Increasing |
Clarity | kHz2 | 0.30 - 0.45 kHz2 | 0.20 - 0.56 kHz2 | Range of sounds made while speaking by changing the shape of tongue, mouth and throat | Increasing |
Crispness | ms | 200 - 300 msec | 100 - 400 msec | Average time of single speech sounds measured from beginning to end of vocal cord vibration | Increasing |
Speech rate | words/min | 75 - 125 words/ min | 0 - 180 words/ min | Number of words spoken per minute | Increasing |
Pause duration | sec | 0.25 - 0.60 sec | 0.1 - 1.0 sec | Average duration of pauses between speech sounds (higher values imply lower mental fitness) | Decreasing |
...
Versions 1-3 are legacy versions; Please refer to Version 4 (For API) or Version 5(For App SDK) document above
MF Acoustic Scores - Version 3
...
The following scores are available through the API (Use Case document )
Acoustic score definitions and range interpretation (this section for app developer reference)
...