By: Joris Castermans

Worldwide, 300 million people suffer from some speech disability. Losing one's voice has profound and far-reaching effects on a person's life. Communication, a fundamental aspect of human existence, becomes a daily challenge, leading to social isolation and frustration as individuals struggle to convey their thoughts, emotions, and needs to others. Professionally, careers may be jeopardized as many occupations require effective verbal communication. This can lead to financial stress and a loss of independence. Moreover, diminished vocal ability can erode self-esteem, leading to feelings of inadequacy and depression.

There is a wide variety of speech disabilities, with different limitations in speaking easily, in-flow, and intelligibly. Therefore, to better understand and categorize the different types of assistive voice technologies, it is important to first have a better understanding of the concept of speech production.

Communication, talking and expressing oneself, is a fundamental human right. Yet several impairments may hinder this ability, leading to various communication challenges. From Augmented Alternative Communication (AAC) tools to the latest real-time assistive voice technology, advancements in this field facilitate communication for those with speech-related disabilities. The world of assistive technologies is vast and varied, catering to many impairments and challenges. However, amidst this backdrop, the positioning of real-time assistive voice technology remains unique.

The Source-Filter Model: Understanding the Speech Impairment Spectrum

The speech impairment spectrum encompasses various conditions affecting an individual's ability to produce clear and compelling speech. These impairments range from articulation disorders, where specific sounds are tricky to pronounce, to fluency disorders, like stuttering that disrupts the flow of speech. Voice disorders affect the pitch, volume, or quality of the voice, while motor speech disorders such as dysarthria and apraxia involve difficulties due to muscle control or neurological issues.

A critical framework used to explain how speech is generated is the "Source-Filter Model.” This model helps us understand how the vibrations produced by the vocal cord (sound source) are modified and shaped by the form and movements of the vocal tract (filter) to produce clear and intelligible speech.

The Source-Filter Model of speech production is a fundamental framework for understanding how humans produce speech sounds. It conceptualizes speech production in two main components: the "source" and the "filter." Let's delve deeper into how this model explains voice quality and articulation. We’ll then explore how this framework can be adapted for individuals using Augmented Alternative Communication (AAC) tools and speech-to-text technologies.

1. The Source: The source of speech is primarily the air pushed out from the lungs that causes the vocal cords within the larynx to vibrate. This vibration produces a fundamental frequency, which is perceived as the pitch of the voice. The nature and intensity of the vibration (e.g., loud or soft, high or low pitch) contribute to the voice quality.

2. The Filter: The filter comprises the articulatory movements of the vocal tract, including the tongue, lips, and palate. Articulation disorders manifest when these movements are imprecise, as seen in conditions like apraxia, or due to structural anomalies. Dysarthria, characterized by weak muscle control affecting the filtering mechanism, results in slurred or slow speech that can be difficult to understand.

Advancements in Supportive Communication Technologies

For individuals facing challenges in both the source and filter components — such as those with no articulation or compromised voice quality — Augmented Alternative Communication (AAC) tools provide significant support. AAC devices range from