AI system helps analyze 'replacement' voices after laryngectomy

AI system helps analyze ‘replacement’ voices after laryngectomy

The voice is a medium we use to successfully interact with the outside world. Unfortunately, most people’s voice changes or even disappears after a laryngectomy. To improve the quality of life of these patients, a team of researchers from the universities of Kaunas, Lithuania, has invented a new surrogate voice assessment index – it will detect patients’ voice pathologies faster and better.

Removal of the larynx – a laryngectomy, usually performed for advanced laryngeal cancer, significantly changes the voice, which significantly interferes with the normal life of the patient. Kaunas University of Technology (KTU IF) Computer Science Faculty researcher Rytis says that voice change after laryngectomy depends on the severity of the situation: “For some, the voice changes only slightly, while that for others it can be a life-changing situation. Imagine calling someone on the phone, emergency services, police, etc. – and that the one you call does not understand anything. Or even not hear you – because the phone’s noise cancellation system will cut it out”.

“These types of surgeries require removal of one or both vocal cords, part or even all of the larynx to remove a malignant tumor from the larynx. As a result, after oncological laryngeal surgery, the voice is extracted using only the laryngeal structures remaining after the operation, which are physiologically not intended for this – we call such a voice a “substitute voice”, explains Prof. Virgilijus Ulozas, professor at the Lithuanian University. Health Sciences University (LSMU). He points out that the quality of voice and speech deteriorates after such an operation, complicating the possibilities of communication and the quality of life of the patients.

Artificial intelligence as a voice analysis assistant

Recently, researchers from KTU and LSMU published a study in which, using artificial intelligence (AI) signal processing, it was possible to determine whether a patient had certain voice pathologies.

According to Maskeliūnas, the idea to study and determine the voice quality of patients after laryngectomy came from a medical team led by an expert in this field, Professor Ulozas. To facilitate and automate the post-operative process, KTU researchers used AI technologies, which allowed them to conditionally replace an expert doctor, a very positive result evaluated in the clinical study.

“Usually the doctor analyzes the voice and provides an indication of the impairment; the patients themselves also complete a questionnaire on their perception of voice quality. Speech signal energy, formants and other parameters are also used during digital signal analysis,” explains Maskeliūnas.

According to him, this study is unique: “Previous studies have never successfully used artificial intelligence as an expert assistant in voice analysis”.

According to the scientist, thanks to this innovation, the post-operative process becomes automated, which allows the implementation of automated screening solutions, allowing doctors to more easily follow and record the evolution of the disease and to establish diagnoses.

New “surrogate” voice rating index shows promise

During the research, the research team from KTU and LSMU is pleased to announce a discovery – the Acoustic Substitute Voice Index (ASVI), which will enable scientists to quantitatively measure and assess voice” substitution” of the patient after oncological laryngitis using acoustic parameters of the voice, signal methods and artificial intelligence.

“Until now, in medical practice, there was no suitable method to objectively and quantitatively assess the ‘surrogate’ voice. Our proposed ASVI algorithm allows the evaluation process to be performed automatically in a concise time,” says Professor Ulozas.

He also believes that this discovery would allow the patient to perform a voice test at home or in a non-specialized medical facility if negative voice changes are seen early. On the other hand, the professor points out that good ASVI indicators, in the absence of other complaints, would allow patients to avoid unnecessary visits to health professionals.

Early ASVI clinical trials are also very optimistic. Another goal of the researchers is to develop a practical and clinically acceptable prototype to measure ASVI in a real clinical setting. For example, it could be a mobile application accessible to both specialists and patients.

In the future, such diagnostic automation will open up new possibilities. To determine the acoustic index of the “surrogate” voice, it will be enough to have a smartphone or any other device with an Internet connection with you. After downloading an audio recording or just speaking, the changes in the voice will be analyzed, the system will show an estimate, based on which further processing will be decided.

Reference: Uloza V, Maskeliunas R, Pribuisis K, Vaitkus S, Kulikajevas A, Damasevicius R. An artificial intelligence-based algorithm for substitute voice assessment. Appl. SCI. 2022;12(19):9748. doi:10.3390/app12199748

This article was republished from the following materials. Note: Material may have been edited for length and content. For more information, please contact the quoted source.

#system #helps #analyze #replacement #voices #laryngectomy

Leave a Comment

Your email address will not be published. Required fields are marked *