It’s no secret. Synthetic voices baked into today’s augmentative and alternative communication (AAC) applications are unnatural and robotic sounding. We’ve discussed this previously here and here.
As SLPs, Behavior Therapists, and Assistive Technology professionals this problem is magnified when we reflect upon the profound importance of voice communication.
What is voice
“Voice” refers to the ability to engage in meaningful conversation, and to make a difference or impact upon key decisions. According to John Paul Lederach, voice centers upon inclusive conversations that are grounded in “mutuality, understanding and accessibility”. [1]
When individuals have a voice, their views, thoughts, and feelings receive a “fair hearing” that is readily recognized by others [2]. They possess the ability to influence outcomes and manipulate contexts with words they speak.
Unfortunately, those without a voice are at a serious disadvantage. AAC applications help to some extent, but without the ability to communicate with emotive and natural sounding synthetic voices, users will struggle to communicate intent and meaning.
Why voice matters
The moment we open our mouths to speak we are judged.
As words are spoken assumptions are made about who we are — presumptions about our intelligence, desires, determination, confidence and influence are all inferred from how we use our voices.
For instance:
- Our tone, pitch, quality of articulation and inflection deliver subtle messages about the kind of person we are. They convey our mood and our feelings at a particular time.
- Having the capacity to project appropriate sounds can make a critical difference in the way we are perceived and treated. When used effectively, our voice can work in our favor and enhance our personal and professional relationships.
- It can be said that our voice is the primary link between our mind and body. Therefore, with the appropriate mindset and awareness of how to use our voice properly, we can exercise control over how we speak, improve effectiveness and do so with confidence.
It’s evident those with communication impairments are at a serious disadvantage. Fortunately, the future of voice synthesis is bright.
What’s next for synthetic voice
Much of the future of synthetic voice will revolve around “emotive analytics.” It’s a new field that focuses on identifying and analyzing the full spectrum of human emotions. Emotive analytics will enable synthetic voice systems to analyze the underlying emotional state of a user’s voice and respond appropriately given a particular scenario.
In the context of AAC applications, emotive analytics and pattern recognition will enable users to add emotional influence to their synthetic voice outputs. Also, much focus will be placed on user experience. In order to add emotion to text-to-speech outputs there will have to be an accessible, intuitive and highly efficient process in place.
Ultimately, future emotive AAC applications will empower users and mimic similar levels of flexibility and capacity as natural voice.
Take Away
As SLPs, Behavior Therapists, and Assistive Technology professionals we understand the power and importance of voice and language. It’s very personal to us and a core component of our identify.
We also understand the power of AAC applications and how they’re used to express thoughts, needs, wants, and ideas for those with communication disadvantages. However, today’s AAC applications lack the ability to supplement one of the most vital characteristics of voice, emotion.
With access to emotive voice, those with communication disadvantages will be better equipped to accurately impart intent and meaning. They will be able to account for context and scenario suitability, and ensure the messages they deliver are appropriately received, with credibility and sincerity.
Emotive voice is staggeringly important to everyday life.
Everyone deserves an emotive voice.
