Voiceitt’s Journey to make speech truly accessible to all

Voiceitt’s Journey to make speech truly accessible to all By Danny Weissberg

augmentative and alternative communication (AAC)

Voiceitt's Journey to make speech truly accessible to all

WHY VOICEITT'S MISSION IS MAKE SPEECH ACCESSIBLE TO ALL: For at least 1.5% of the world’s population, over 120 million people, communicating verbally is not an option as a result of medical conditions. These conditions, collectively called dysar- thria, result in speech that is very difficult to understand. Nearly 20% of all individuals will have suffered a cerebrovas- cular stroke by the time they reach 75, resulting in slurred speech for half of that group. Other causes of dysarthria and impaired speech include amyotrophic lateral sclerosis (ALS), Parkinson’s disease (PD), brain cancer, and traumatic brain injury (TBI). Due to lack of neurological and motor control (often accompanied by other physical limitations), their speech impairments make it difficult for them to complete simple tasks like ordering a coffee, saying hello to a friend, and using a smart home device to control their home environment. Voice-driven technologies are increasingly mainstream. If the skyrocketing sales of voice activated devices worldwide are any indicator, it is likely that voice will soon become a primary means by which we interact with the world around us. For most of us, voice-activation can be convenient and fun. But for people with motor control challenges and speech disabilities, the ability to navigate the environment and control devices by voice can be life changing. However, many of the people who can potential- ly benefit from a so-called “voice first” world cannot access these technologies because along with motor control challenges, they do not have standard speech patterns.

When designing an automatic speech recognition (ASR) tech- nology for dysarthric speech, one needs to consider that pronun- ciation ‘distortion’ cannot always be described as simple sound substitutions or deletions. Motor impediments in speech organs Voiceitt App

DANNY WEISSBERG Co-Founder & CEO of Voiceitt is an engineer-turned-serial entrepreneur with 15 years of experience in entrepreneurship, business development, management, innovation, research and development in cutting edge technologies of complex software solutions. Danny also has specific distinction in R&D, having excelled through various points of his career at leading Israeli software firms CheckPoint, HP, and Radvision (now Cisco). Danny graduated with a B.Sc. with Honors in from the Technion – Israel Institute of Technology, a B.A. in Computer Science with Honors from the Open University of Israel. The idea for Voiceitt was born when Danny Weissberg’s grandmother had a severe stroke. Very suddenly she lost her ability to speak clearly and be understood by the people around her, including her close family. This immediately Danny, who had been unusually close with her since he was a toddler, felt her pain and frustration as she struggled to communicate basic human needs.

December, 2020 / January, 2021 | www.closingthegap.com/membership

BACK TO CONTENTS

lead to both (involuntary) asynchrony between articulatory ges- tures and (voluntary) alternative articulatory strategies, which in turn yield insertion of sounds not found in the target words, splits of target sounds (one to many), repetitions of target sounds, substitutions of entire sound sequences (many to many) and in- sertions of pauses inside words. For example, too early opening of the nasal passage to airflow, which reduces air pressure above the vocal folds and facilitates their vibration, often results in the presence of an unexpected nasal consonant (like n or m) before another consonant, or of nasal coloring of an entire syllable. Recognizing the complexity and the unique needs and char- acteristics of the users it serves, the core technology that forms Voiceitt’s multi-layered solution is built upon two main ASR archi- tectures adapting state-of-the-art ASR techniques to recognize dysarthric speech. Voiceitt's is an accessible app, designed to serve individuals with dysarthria caused by medical conditions, such as Cerebral Palsy, Stroke, ALS, Parkinson’s disease, Down's syndrome, Trau- matic Brain Injury and any other type of non-standard speech to communicate and control smart assistants with their OWN VOICE for the first time. Voiceitt’s app identifies and adapts to the individ- ual’s unique impaired speech patterns like breathing pauses and

non-verbal sounds so that individuals with severe speech impair- ment can use it to communicate. Voiceitt does not need an Inter- net connectivity for usage and can be used everywhere. Technologically, Voiceitt lives in a world where all state-of-the- art ASR (Automatic Speech Recognition) systems are designed to recognize standard speech in a variety of native languages from around the world. Being a speech recognition technology that aims to serve millions of individuals around the world with im- paired speech, Voiceitt cannot use existing ASR systems as they were initially designed - we innovatively combine systems, tools, methodologies, sometimes even pure theoretical research in the field of speech recognition, and apply everything in an app that intelligently recognizes the user’s unique speech patterns and translates his speech into standard pronunciation which other people (and smart assistants) can understand. Voiceitt builds a custom ASR speech model, to each user, us- ing machine learning, utilizing deep neural networks, we extract unique speech features used to train our system with the individ- ual’s speech. Once ready, the personal custom ASR model is load- ed into the app where it is used to identify the user’s speech and translate it. It is very unique in a sense that it naturally uses speech/voice

BACK TO CONTENTS

Voiceitt Communication - https://www.youtube.com/watch?v=WRZmoZOtvc0

recognition for communication instead of the traditional use of communication boards that require tapping, and picking through hundreds to thousand words and expressions in their dictionary. No other technology currently allows individuals with mild- severe speech impairment, including non-verbal sounds to com- municated and express their needs naturally and freely with their own voice while supporting large spectrum of speech impair- ments. Current Assistive technology solutions DO NOT support speech as a communication option (only text). At the moment, individuals with speech impairment cannot use any type of smart assistant device because those assistants cannot understand non-standard speech. Voiceitt allows for the first time for individuals with speech impairments to use a voice activated technology that is already mainstream and include population with speech impairments in this technology. This as- sist them to be more independent, do tasks on their own without depending on external help. Voiceitt can be used in every language, in every country- the app is language independent therefore no matter which lan- guage you speak - Voiceitt will translate the non-standard speech to standard speech.

SO HOW DID WE BUILT VOICEITT? Through our journey, we had the honor to meet our future customers and to dive into their sometimes complexed reality of their day to day and communication obstacles in specific. We had the rare opportunity that not every company has, to build our app together with the people that are going to use it. We have received the most genuine feedback along with their own unique story and experience. Being an app that is supposed to serve individuals with not only speech, but also motor disabilities, the app was designed with high degree of usability in mind. The app’s design promotes user independence and social participation throughout its user workflows, applying simple to use interactions, accessible screen components’ design (large components, high contrast colors, and audible aids. It also supports full interaction with accessibility switches - all of this to allow the user with an app they feel com- fortable with, that is easy for them to use, and that gives them a sense of independence. The app was also designed to offer the user quick wins and celebrating them with encouraging animations - i.e. showing the users that the app recognizes them for the very first time. This is

December, 2020 / January, 2021 | www.closingthegap.com/membership

BACK TO CONTENTS

extremely important and all our users come to use the app be- cause their speech is unintelligible to most unfamiliar listeners. Voiceitt has been tested and used by hundreds of users who provided profound usage feedback allowing us to create a tru- ly accessible communication solution customized to our users’ unique speech and usage characteristics Recently we have started a community release program that allows users to experience the app and communicate with the help of it. We found out an interesting fact – the type of usage is unique to every user: some of them rely on Voiceitt to be their voice: this is actually the only way for them to connect with their own voices and express their needs. Others use Voiceitt as a 'help- er' to cope with words that they find difficult to pronounce or for explaining. Our journey did not finished yet. Our mission is to continue and help people with non-standard speech express themselves and achieve independence using their own voices. The voice tech- nology revolution is leaving people out. We promote inclusion of individuals with speech impairments in our society by giving them their own voice back and the ability to use it on their day to day. We strive to enlarge their possibilities to communicate with others and control their own environment to gain independence.

Visit Voiceitt website: www.voiceitt.com

BACK TO CONTENTS

Page 1 Page 2 Page 3 Page 4

www.closingthegap.com

Made with FlippingBook Ebook Creator