Power the conversation with Signia Integrated Xperience and RealTime Conversation Enhancement
Created Updated
Written by Niels Søgaard Jensen, Barinder Samra, Homayoun Kamkar Parsi, Sascha Bilert, Brian TaylorAbstract
Group conversations in background noise are among the most challenging situations for people with hearing loss, and many hearing aid wearers find it hard to participate and contribute when being in a group conversation, especially in noise. In this paper, we present RealTime Conversation Enhancement technology, which is part of the Signia Integrated Xperience platform, as a solution to the problems experienced in group conversions in noisy environments. Using a new multi-stream architecture, RealTime Conversation Enhancement analyzes the conversation situation, detects conversation partners and creates a live auditory space, which augments the speech and immediately adapts to changes in the conversation layout. Results from a study on the perceptual effects show that a significant improvement in speech understanding is offered by RealTime Conversation Enhancement. In a test simulating a group conversation scenario, 95% of the participants showed better performance with RealTime Conversation Enhancement.
Discussion
The results in this study pointed in the same and unambiguous direction: In both speech tests, adding RTCE with its multi-stream architecture to the existing split processing offered a significant improvement in the participants’ ability to understand speech in the challenging conditions.
While the standard OLSA test is a fairly simple test, it offers a good simulation of a typical one-on-one conversation where the hearing aid wearer is facing a conversation partner with noise coming from behind. In the test, a mean SRT80 improvement of 1.6 dB was observed. Based on the value of the slope of the underlying psychometric function of the standard OLSA test provided by Wagener & Brand (2005), an improvement of 1.6 dB corresponds to around 25% better speech understanding. This observed benefit indicates how RTCE can have a substantial impact also in ‘simple’ conversation setups where the ability to adapt to the conversation layout allows more focus on the conversation partner in front. While the same effect in principle could be obtained with a narrow beamformer, the narrow beamformer would not allow the wearer to turn their head during the conversation or allow a third person to enter the conversation (without missing out). Due to its continuous analysis and adaptation to the conversation layout, RTCE allows such actions, which contribute to a more natural listening experience where the wearer can feel fully immersed in the context of the conversation.
In the modified OLSA test, the test scenario was more complex and much closer to a group conversation scenario with speech coming from different directions in front of the participant and with fluctuating babble noise coming from different directions behind the participant. The increased complexity was directly reflected in mean SRT80 values being around 5 dB higher compared to the values observed in the standard test. Having more than one target direction and using spatially distributed speech babble as masking noise (in a more reverberant room) simply makes the test more difficult than the standard test at a given SNR.
The most important and noteworthy result in the modified OLSA test is that RTCE also provides a substantial benefit in group conversations. It was a striking observation that 95% of the participants performed better in the test with RTCE turned on. The observed highly significant mean SNR benefit of 1.1 dB corresponds to an improvement in speech understanding of close to 20% (using the same value of the slope of the psychometric function as used for the standard OLSA test; Wagener & Brand, 2005). This will offer the wearer a clear benefit in a group conversation, compared to not having access to RTCE.
In combination, the results from the two tests indicate that RTCE provides a substantial benefit in different types of conversation layouts, including both one-on-one conversations and more complex conversation scenarios with multiple conversation partners. When the study results are coupled with RTCE’s ability to track and adapt to changes in the conversation layout, it is evident that RTCE offers completely new possibilities for wearers who want to fully engage in a conversation.
The improvement in speech understanding offered by RTCE not only allows the wearer to understand more when being part of a conversation, it also enables the wearer to contribute more actively – and more confidently – to the conversation. The less the wearer must struggle to understand their conversation partners, the more cognitive resources can be saved. These resources instead can be spent on the task of responding to what is being said, and the wearer thereby is empowered to contribute more to the conversation.
From this perspective, it is important that all voices, both those of conversation partners and the wearer’ own voice, are processed optimally. This makes Signia IX’s Own Voice Processing (OVP) 2.0 another critical element in the hearing care professional’s toolbox. Optimizing the sound of the wearer’s own voice can positively impact the wearer’s contribution to conversations (Powers et al., 2018). The ability of OVP 2.0 to improve the perception of own voice (Jensen et al., 2022) – also in situations with background noise – is therefore a vital element of the wearer’s conversation experience. It is worth mentioning that in cases where wearers use Signia Assistant to report perceptual problems in a given listening situation, both RTCE and OVP 2.0 performance can be adjusted to improve the listening experience. Given these fine-tuning capabilities, Signia Assistant is a powerful tool for wearers looking for improvements in conversational situations.
Summary
In this paper, we have described the new RealTime Conversation Enhancement technology with its multi-stream architecture, which is introduced on the Signia Integrated Xperience platform. The aim of the technology is to enable wearers to increase their engagement in conversations, especially in dynamic group conversations where background noise is present.
By applying a highly advanced sound analysis, RTCE can detect the locations of relevant conversation partners. The multi-stream architecture creates an auditory space where the conversation partners are augmented, making it easier for the wearer to participate in and contribute to the conversation. By updating the system 1,000 times a second, it adapts to any changes in the conversation layout, e.g., when talkers move or when the wearer turns their head.
The perceptual benefits of RTCE were investigated in a study. The main conclusions were:
- In a simple speech test simulating a one-on-one conversation with the conversation partner situated in front of the participant, activating RTCE provided a significant improvement in speech understanding with 90% of the participants showing better performance with RTCE.
- In a more complex speech test, simulating a group conversation scenario, with conversation partners speaking alternately from directions to the left and right of the participant, activating RTCE also provided a significant improvement in speech understanding with 95% of the participants showing better performance with RTCE.
- In combination, the results from the two tests suggest that RTCE can significantly improve the wearer’s conversational experience, making it easier to understand and contribute to the conversation.
References
Best S., Serman M., Taylor B. & Høydal E.H. 2021. Augmented Focus. Signia Backgrounder. Retrieved from www.signia-library.com.
Eberts S. 2020. Dining Out for People with Hearing Loss. The Hearing Journal, 73(1), 16.
Jensen N.S., Høydal E.H., Branda E. & Weber J. 2021. Augmenting speech recognition with a new split-processing paradigm. Hearing Review, 28(6), 24-27.
Jensen N.S., Pischel C. & Taylor B. 2022. Upgrading the performance of Signia AX with Auto EchoShield and Own Voice Processing 2.0. Signia White Paper. Retrieved from www.signia-library.com.
Nicoras R., Gotowiec S., Hadley L.V., Smeds K. & Naylor G. 2022. Conversation success in one-to-one and group conversation: a group concept mapping study of adults with normal and impaired hearing. International Journal of Audiology, 1-9.
Petersen E.B., MacDonald E.N. & Sørensen A.J.M. 2022a. The Effects of Hearing-Aid Amplification and Noise on Conversational Dynamics Between Normal-Hearing and Hearing-Impaired Talkers. Trends in Hearing, 26, 1-17.
Petersen E.B., Walravens E. & Pedersen A. 2022b. Real-life Listening in the Lab: Does Wearing Hearing Aids Affect the Dynamics of a Group Conversation? Proceedings of the 26th Workshop on the Semantics and Pragmatics of Dialogue, August 22-24, 2022, Dublin.
Picou E.M. 2022. Hearing aid benefit and satisfaction results from the MarkeTrak 2022 survey: Importance of features and hearing care professionals. Seminars in Hearing, 43(4), 301-316.
Powers T.A., Davis B., Apel D. & Amlani A.M. 2018. Own Voice Processing Has People Talking More. Hearing Review, 25(7), 42-45.
Taylor B. & Jensen N.S. 2022. Evidence Supports the Advantages of Signia AX's Split Processing. Signia White Paper. Retrieved from www.signia-library.com.
Taylor B. & Jensen N.S. 2023. Unlocking Quality of Life Benefits Through Firmware and Apps. Hearing Review, 30(5), 24-26.
Wagener K., Brand T. & Kollmeier B. 1999. Entwicklung und Evaluation eines Satztests für die deutsche Sprache. I-III: Design, Optimierung und Evaluation des Oldenburger Satztests (Development and evaluation of a sentence test for the German language. I-III: Design, optimization and evaluation of the Oldenburg sentence test). Zeitschrift für Audiologie (Audiological Acoustics), 38, 4-15.
Wagener K.C. & Brand T. 2005. Sentence intelligibility in noise for listeners with normal hearing and hearing impairment: influence of measurement procedure and masking parameters. International Journal of Audiology, 44(3), 144-156.