The Growing Role of AI in Speech Therapy
Published on: May 23, 2024
AI in speech rehabilitation featured image
Article author photo

Elena Paspel

Master of Science in Engineering (Digital Health) - <a href="https://taltech.ee/en/" rel="nofollow">Tallinn University of Technology, Estonia</a>

Article reviewer photo

Valentina Levi

BSc Biomedical Sciences (Hons) Neuroscience, The University of Edinburgh

Introduction: Bridging gaps in speech therapy with AI

Speech disorders affect millions of people worldwide, impacting their ability to communicate effectively. Traditionally, speech therapy involves working one-on-one with a speech-language pathologist (SLP) to improve speech production. However, there is a shortage of SLPs globally and access to care can be limited, especially in rural areas. Enter artificial intelligence (AI). Recent advances in artificial intelligence (AI) are providing new tools to help meet the need for speech therapy. Enhancing speech therapy with AI-enabled tools heralds a new era of accessible, effective, and personalised care for individuals with speech disorders, bridging the gap between the need for therapy and the availability of specialised care.

What is speech therapy?

Speech therapy is a supportive guide for those who struggle to speak or understand speech. It helps people of any age who find it hard to talk, from pronouncing words to forming full sentences and possibly even swallowing. Think of it as a set of tools designed to address various speech and language challenges. Whether it's young children mixing up sounds or adults recovering from a stroke and struggling to find words, speech therapy offers support.

This therapy goes beyond just speaking. It aims to improve understanding and communication. It assists children who struggle to name objects or express their thoughts and helps adults regain lost speech abilities due to injury or illness. Some individuals may have difficulty producing sounds correctly or being understood. Others may experience unusual voice changes or swallowing difficulties, which can be alarming. However, speech therapy provides solutions for these issues too.

Transforming stuttering therapy with AI

Detecting stuttering: AI tools can listen to speech patterns and pinpoint exactly when and how stuttering occurs. This is like having a highly skilled therapist who can catch every stutter, even those that might not be obvious.1

Personalised therapy: By understanding each person's unique speech patterns, AI can help create customised therapy plans. This means therapy can be more effective because it targets the specific needs of each individual.1

Improving accuracy: Traditional methods might miss subtle stutters or misclassify them. AI, with its ability to analyse large amounts of data quickly, reduces these errors, offering a clearer picture of a person's speech challenges.1

AI-enhanced hearing aids as tools for speech therapy

Modern hearing aids, equipped with AI and machine learning algorithms, do more than amplify sound. They distinguish between speech and noise, enhance speech clarity, and adjust settings in real-time to optimise the user's hearing experience in various environments.2

AI improves speech clarity in noisy environments

A core challenge for people with hearing loss is understanding speech in noisy settings. AI-powered hearing aids tackle this by processing, identifying and amplifying speech, making it easier for the user to understand conversations even in noisy environments.2 This not only aids in more effective communication but also supports the goals of speech therapy by improving the wearer's ability to engage in conversational speech and comprehend spoken language in complex acoustic environments​.

Direct Applications in Speech Therapy: For speech therapy specifically, the advancements in hearing aid technology mean therapists can utilise these devices as part of their therapeutic toolkit. By improving the audibility and clarity of speech sounds, hearing aids help individuals practise and reinforce speech therapy techniques in real-life scenarios, thus bridging the gap between therapy sessions and daily communication needs.

Integrating tele-audiology into speech therapy

Tele-audiology addresses multiple barriers to hearing healthcare, including geographical, financial, and logistical challenges. Tele-audiology, powered by AI, extends beyond traditional audiological care, offering remote hearing screenings, diagnostic tests, intervention, and rehabilitation. By providing services remotely, AI can enable individuals in remote or underserved areas to receive timely and effective audiological care, thereby supporting concurrent speech therapy programs. This approach is beneficial for patients and healthcare providers, allowing for a more efficient allocation of resources and enabling specialists to reach a wider patient base.3 

One significant advancement in tele-audiology is the development of AI algorithms to improve the sensitivity and specificity of home-based otoscopy, making remote diagnosis and treatment of ear conditions more reliable​​.3 Additionally, smartphone-based machine learning algorithms have been used to detect middle ear fluid, demonstrating the potential for AI to enhance diagnostic accuracy in tele-audiology.3

AI-powered tele-audiology significantly benefits speech therapy by ensuring that individuals with hearing impairments receive timely and effective support, which is crucial for the successful treatment of speech disorders. By leveraging tele-audiology services, speech therapists can work in concert with audiologists to provide a cohesive treatment plan that addresses patients' audiological and speech-related needs.

Timely audiological intervention is crucial in preventing and mitigating speech and language development delays in children with hearing loss.3 By providing remote access to audiological services, tele-audiology can expedite the diagnosis and treatment of hearing impairments, thereby facilitating earlier and more effective speech therapy interventions. This not only helps in improving speech and language outcomes but also supports the overall academic and social development of children. 

Moreover, AI-driven tele-audiology services, such as remote hearing aid fittings and cochlear implant programming, may empower patients with more control over their care, potentially leading to increased satisfaction and adherence to treatment plans.3

Next-generation speech therapy: AI and brain-computer interfaces 

AI has the potential to advance speech therapy through brain-computer interface (BCI) technologies. By analysing EEG signals, AI algorithms can interpret the brain's electrical activity as speech, offering new communication avenues for individuals with severe speech impairments.4 

This approach bridges audiology and speech therapy by translating thought into spoken word, bypassing traditional speech production pathways. Techniques such as support vector machines and deep learning, particularly convolutional neural networks, have shown promise in decoding imagined speech, underscoring the synergy between AI's analytical capabilities and the therapeutic goals of speech therapy. This integration could dramatically enhance treatment options for speech disorders, underscoring the importance of interdisciplinary collaboration in harnessing AI's potential for healthcare.

Overcoming challenges in AI-driven speech therapy

Despite its promise, the integration of AI into speech therapy faces hurdles, such as the need for diverse and comprehensive speech datasets.1Crucially, more research and collaboration are necessary to refine AI tools, ensuring they can serve a broader spectrum of individuals facing speech disorders. Moreover, BCI technology development is still in its infancy.4 However, as AI continues to evolve, its potential to revolutionise speech therapy grows.

Summary

AI is changing the field of speech therapy, making treatments more personalised, accessible, and effective. It highlights the technology's potential to improve care for people with speech disorders and the ongoing work needed to fully realise this potential.

Key points:

AI in stuttering therapy: Artificial Intelligence (AI) tools can identify stuttering by listening to speech patterns, and offering personalised therapy plans based on each individual's unique needs. This precision and customisable nature means therapy is more effective, targeting the specific challenges of each person.

AI-enhanced hearing aids: Modern hearing aids, equipped with AI, do more than make sounds louder. They can tell the difference between speech and background noise, making it easier for people to understand what others are saying, even in noisy places. This technology is a great tool for speech therapy because it helps people practise hearing and speaking clearly in real-world situations.

Tele-audiology powered by AI: Tele-audiology uses AI to provide hearing care over the Internet. This is especially helpful for people who live far from specialists. It includes everything from hearing tests to fitting hearing aids remotely, making sure that people can get the help they need without travelling. For speech therapy, it means therapists and audiologists can work together more easily to help individuals.

Brain-computer interface (BCI) and speech therapy: AI is also exploring ways to use brain-computer interfaces (BCIs) to help people with severe speech impairments. AI can help translate thoughts into speech by reading the brain's electrical signals. This cutting-edge technology could open new doors for people who struggle to speak in traditional ways.

Challenges and future directions: While AI offers many exciting possibilities for speech therapy, there are still challenges to overcome. One big issue is ensuringAI tools can understand and help with a wide range of speech disorders. More research and teamwork are needed to make AI a common part of speech therapy, but the future looks promising.

References

  1. Alnashwan R, Alhakbani N, Al-Nafjan A, Almudhi A, Al-Nuwaiser W. Computational intelligence-based stuttering detection: a systematic review. Diagnostics (Basel) [Internet]. 2023 Nov 27 [cited 2024 Feb 26];13(23):3537. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10706171/ 
  2. Fabry DA, Bhowmik AK. Improving speech understanding and monitoring health with hearing aids using artificial intelligence and embedded sensors. Semin Hear [Internet]. 2021 Aug [cited 2024 Feb 26];42(3):295–308. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8463124/ 
  3. D’Onofrio KL, Zeng FG. Tele-audiology: current state and future directions. Front Digit Health [Internet]. 2022 Jan 10 [cited 2024 Feb 26];3:788103. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8784511/ 
  4. Shah U, Alzubaidi M, Mohsen F, Abd-Alrazaq A, Alam T, Househ M. The role of artificial intelligence in decoding speech from eeg signals: a scoping review. Sensors (Basel) [Internet]. 2022 Sep 15 [cited 2024 Feb 26];22(18):6975. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9505262/ 
Share

Elena Paspel

Master of Science in Engineering (Digital Health) - Tallinn University of Technology, Estonia

Bachelor of Laws - LLB (Hons), London Metropolitan University, UK

An experienced professional with a diverse background spanning law, pricing, and eHealth/Digital Health. Proficient in copywriting, medical terminology, healthcare interoperability standards, and MedTech regulations. A strong foundation in scientific research methodologies and user experience research supports the creation of compelling content for the biopharmaceutical, CROs, medical technology, and eHealth sectors.

Proven expertise in driving product vision, synthesizing complex information, and delivering user-centric solutions. Adept at streamlining workflows and processes, and drafting documentation and SOPs. Always open to collaborations and eager to connect with like-minded professionals.

arrow-right