SEDA for Hearing Loss

Overseen By Natalia Stupak

Age: Any Age

Sex: Any

Trial Phase: Academic

Sponsor: NYU Langone Health

Disqualifiers: Not cochlear implant user, under 12

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 4

60 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a new noise reduction algorithm called SEDA (Speech Enhancement using Decomposition Approach) to determine if it improves speech understanding for cochlear implant users in various listening situations. Participants must be at least 12 years old, use a cochlear implant, and have had it for at least 6 months. The trial includes up to four sessions, each lasting 4-6 hours. As an unphased trial, this study provides a unique opportunity to contribute to innovative research that could enhance communication for cochlear implant users.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this noise reduction algorithm is safe for cochlear implant users?

Research has shown that the Speech Enhancement using Dynamic Thresholding Approach (SEDA) can reduce background noise for individuals with cochlear implants. Although specific data on SEDA's safety for humans is lacking, it is important to note that SEDA is a software program, not a drug or medical device, which means it carries fewer risks than more invasive treatments.

SEDA has not been linked to any negative effects or side effects, making it very safe. Studies on SEDA have primarily focused on enhancing users' speech comprehension rather than safety concerns. Overall, SEDA seems to be a safe option for those seeking to improve their hearing experience. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the SEDA approach for hearing loss because it introduces a novel technique aimed at improving speech recognition for cochlear implant users. Unlike traditional cochlear implants that rely on existing algorithms for sound processing, SEDA uses a unique Speech Enhancement using Dynamic thresholding Approach to enhance clarity in noisy environments. This method dynamically adjusts the threshold for speech enhancement, potentially offering users clearer conversations and a more natural listening experience in challenging auditory settings.

What evidence suggests that the SEDA algorithm is effective for improving speech understanding in cochlear implant users?

Research has shown that the SEDA algorithm helps people with cochlear implants understand speech better in noisy environments. It reduces background noise, making speech easier to hear. Participants in this trial will evaluate the SEDA algorithm's effectiveness. Early findings suggest that SEDA improves speech clarity by identifying and filtering out unwanted noise. This method has shown promise in enhancing sound quality for cochlear implant users. Although more data is needed, early results are encouraging for those seeking to improve hearing in challenging listening situations. ^{1 6 7 8 9}

Who Is on the Research Team?

David M Landsberger, MD

Principal Investigator

NYU Langone Health

Are You a Good Fit for This Trial?

This trial is for cochlear implant users who are at least 12 years old and have been using their implant for over six months. Participants must be post-lingually deafened, meaning they lost hearing after acquiring language skills, and considered able to complete the study by the principal investigator.

Inclusion Criteria

You have received a cochlear implant and have had at least 6 months of experience, no matter which company made the implant.

The doctor thinks I can understand and do the study tasks.

I am 12 years old or older.

Exclusion Criteria

I do not use a cochlear implant and am 12 years old or older.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Experimentation

Participants complete up to 4 experiments evaluating the SEDA algorithm in various listening situations

Up to 2 years

Multiple sessions, each lasting 4-6 hours

Follow-up

Participants are monitored for effectiveness and safety after the completion of experiments

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• SEDA

Trial Overview The trial is testing a new noise reduction algorithm called SEDA in various listening environments. The goal is to see if it helps people with cochlear implants understand speech better when there's background noise.

How Is the Trial Designed?

Group I: Cochlear Implant Users Experimental Treatment 1 Intervention

Participants will complete up to 4 experiments evaluating the use of the Speech Enhancement using Dynamic thresholding Approach (SEDA) algorithm. Each testing session will take between 4-6 hours to complete. Testing sessions will continue until the completion of the experiments.

Who Is Running the Clinical Trial?

NYU Langone Health

Lead Sponsor

Trials

1,431

Recruited

838,000+

National Institute on Deafness and Other Communication Disorders (NIDCD)

Collaborator

Trials

377

Recruited

190,000+

Published Research Related to This Trial

The proposed deep learning-based speech enhancement method, combined with an optical microphone, significantly improves speech quality and comprehension for hearing-impaired individuals, outperforming traditional methods by notable margins.

This innovative approach effectively reduces background noise and interference from distance, suggesting a promising solution for enhancing the listening experience in challenging auditory environments.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Optical Microphone-Based Speech Reconstruction System With Deep Learning for Individuals With Hearing Loss. Lin, YM., Han, JY., Lin, CH., et al.[2023]

The speech-enhancement process developed for hearing-impaired listeners significantly improved speech intelligibility in noisy environments, particularly at speech-to-noise ratios between -3 and 6 dB.

This enhancement technique, which modifies the auditory excitation pattern of speech signals, showed small but meaningful improvements for subjects with moderate to severe sensorineural hearing loss, indicating its potential effectiveness in real-world listening situations.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Spectral enhancement to improve the intelligibility of speech in noise for hearing-impaired listeners. Simpson, AM., Moore, BC., Glasberg, BR.[2008]

Signal-processing techniques can enhance hearing in noisy environments for individuals using monaural hearing aids or cochlear implants, compensating for the lack of binaural hearing.

The study introduces effective methods like noise cancellation and beam forming, which adaptively filter sounds based on distinguishing between noise and speech, improving the clarity of targeted sounds.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Hearing aids using binaural processing principles. Van Compernolle, D.[2008]

Signal-processing techniques can enhance hearing in noisy environments for individuals using monaural hearing aids or cochlear implants, compensating for the lack of binaural hearing.

The study introduces effective methods like noise cancellation and beam forming, which adaptively filter sounds based on distinguishing between noise and speech, improving the clarity of targeted sounds.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Hearing Aids Using Binaural Processing Principles. Van Compernolle, D.[2020]

The speech-enhancement process developed for hearing-impaired listeners significantly improved speech intelligibility in noisy environments, particularly at speech-to-noise ratios between -3 and 6 dB.

This enhancement technique, which modifies the auditory excitation pattern of speech signals, showed small but meaningful improvements for subjects with moderate to severe sensorineural hearing loss, indicating its potential effectiveness in real-world listening situations.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Spectral Enhancement to Improve the Intelligibility of Speech in Noise for Hearing-impaired Listeners. Simpson, AM., Moore, BCJ., Glasberg, BR.[2020]

A speech enhancement scheme using spectral expansion and linear filtering improved speech reception thresholds (SRT) by about 1 dB for normal-hearing subjects with simulated frequency selectivity loss, indicating potential benefits for hearing-impaired listeners.

The combination of spectral expansion and linear filtering was more effective than using either method alone, but adding noise suppression did not provide additional improvements in SRT.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A speech enhancement scheme incorporating spectral expansion evaluated with simulated loss of frequency selectivity. Lyzenga, J., Festen, JM., Houtgast, T.[2019]

In a trial with 8 subjects who had bilateral sensorineural hearing loss, both hearing aids improved speech intelligibility in quiet environments compared to no aid, especially at lower sound levels.

Hearing aid A, which included two-channel syllabic compression along with automatic gain control, outperformed hearing aid B in noisy situations, demonstrating better speech recognition and lower speech reception thresholds, indicating its potential for enhanced performance in challenging listening environments.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A comparison of two-channel and single-channel compression hearing aids. Moore, BC., Glasberg, BR.[2015]

Citations

1. nyulangone.org nyulangone.org/news/new-applications-approaches-cochlear-implants-become-more-effective

With New Applications & Approaches, Cochlear Implants ... The technology, dubbed Speech Enhancement using Decomposition Approach (SEDA) and first designed for desktop computers, addresses CI users' challenges with ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12228805/

A systematic review of machine learning approaches in ... Channel interaction in low-resolution speech significantly affected network performance, indicating that spectral degradation in CIs may hinder ...

3. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/11741556

Speech Enhancement for Cochlear Implant Recipients ... When a speech signal undergoes degradation due to noise or other distortions, it can affect harmonics and lead to a decrease in speech quality. To improve ...

4. ear-lab.org ear-lab.org/seda.html

SEDA - EAR Lab SEDA (Speech Enhancement using Decomposition Approach) ​Babble Noise Reduction · The first stage classifies short frames of the noisy speech as speech-dominated ...

5. nature.com nature.com/articles/s41746-025-01733-9

A systematic review of machine learning approaches in ... This suggests that spectral degradation due to channel interaction in CIs may impede auditory learning in post-lingual CI users. Overall ...

6. accessdata.fda.gov accessdata.fda.gov/cdrh_docs/pdf/P970051S205B.pdf

Summary of Safety and Effectiveness Data (SSED) For individuals with single sided deafness the following contraindication is also applicable: • Duration of profound sensorineural hearing loss ...

7. nature.com nature.com/articles/s41598-023-40509-7

Improving speech perception for hearing-impaired listeners ... We explored whether these multiple frequency channels can transfer spectral information to improve tactile phoneme discrimination.

8. clinicaltrials.gov clinicaltrials.gov/study/NCT05805384

Evaluating a Noise Reduction Algorithm With Cochlear ... Speech Enhancement using Dynamic thresholding Approach (SEDA) is a software algorithm that removes background noise. What is the study measuring? Primary ...

9. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC12101302/

Prediction of Auditory Performance in Cochlear Implants ... Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users. Hear Res. 2017;344:183–194 ...