Speech Enhancement for Secure Communication Using Coupled Spectral Subtraction and Wiener Filter

Pardede, Hilman F.; Ramli, Kalamullah; Suryanto, Yohan; Hayati, Nur; Presekal, Alfan

doi:10.3390/electronics8080897

Cited by 9 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The specialized technical feature of relevant innovation themes includes 5G wireless security architecture based on identity management and flexible authentication, as proposed by [44]. An example of applied innovation is the research by [46] proposing speech enhancement for secured voice communication using a technique of coupled Spectral Subtraction and the Wiener Filter.…”

Section: ) 5g Innovation Should Provide Improve the Users' Confidencmentioning

confidence: 99%

Managing 5G Technology: Using Quality of Experience (QoE) to Identify the Innovation Enhancement Pattern According to the Indonesian Market

Suryanegara

2020

IEEE Access

View full text Add to dashboard Cite

The coevolution of 5G technological development and the growing market toward the 5G era has generated an innovation enhancement pattern. Identifying this pattern will reveal the 5G services in demand in the market and the infrastructure required for improving the 5G era. Herein, the patterns of 5G technological innovation enhancements are identified as expected in the Indonesian market. We use a novel approach that combines the users' accumulated experience of mobile technology and market expectation. Two types of questionnaires are developed for this purpose: the first determines the quality of experience (QoE) parameters of 4G compared to the preceding 3G and 2G generations and the second analyzes the expectation of QoE parameters for 5G. This study defines 15 QoE parameters reflecting the aspects of infrastructure and services together with their impact on users. The users' answers are classified into six clusters, which are translated into the innovation enhancement pattern. The findings reveal a pattern in which the Indonesian market is predominantly characterized by satisfied users who expect 5G to provide a better experience than 4G, 3G, and 2G despite the presence of some disappointed users in the market who require specialized innovation with variation in disruptive ways. In terms of 5G infrastructure, certain essential patterns include innovation enhancement to serve remote areas, the increasing significance of connectivity to non-cellular and free-service applications, and the market's constant requirement for a better handset while the local industry may harness the opportunity to complete the 5G ecosystem. In terms of service, essential patterns include a strong need for 5G service innovation to render users more innovative, maintaining societal values while delivering the service, and the service innovation required to connect religious life and the 5G service, which should make users feel more healthy and fit. Finally, we discuss how the patterns recognized herein can help mobile operators to develop appropriate strategies for successfully implementing 5G technology.

show abstract

Section: ) 5g Innovation Should Provide Improve the Users' Confidencmentioning

confidence: 99%

Managing 5G Technology: Using Quality of Experience (QoE) to Identify the Innovation Enhancement Pattern According to the Indonesian Market

Suryanegara

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The technique focused on mapping the observed signal to a clean signal, suppressing the noise subspace. Though the subspace-based speech enhancement deals with noise distortion, it is also used to remove colored noise [20].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Speech Enhancement Algorithm for Voice Assistance Application

Gnanamanickam

Natarajan

Preethaa

2021

Sensors

View full text Add to dashboard Cite

In recent years, speech recognition technology has become a more common notion. Speech quality and intelligibility are critical for the convenience and accuracy of information transmission in speech recognition. The speech processing systems used to converse or store speech are usually designed for an environment without any background noise. However, in a real-world atmosphere, background intervention in the form of background noise and channel noise drastically reduces the performance of speech recognition systems, resulting in imprecise information transfer and exhausting the listener. When communication systems’ input or output signals are affected by noise, speech enhancement techniques try to improve their performance. To ensure the correctness of the text produced from speech, it is necessary to reduce the external noises involved in the speech audio. Reducing the external noise in audio is difficult as the speech can be of single, continuous or spontaneous words. In automatic speech recognition, there are various typical speech enhancement algorithms available that have gained considerable attention. However, these enhancement algorithms work well in simple and continuous audio signals only. Thus, in this study, a hybridized speech recognition algorithm to enhance the speech recognition accuracy is proposed. Non-linear spectral subtraction, a well-known speech enhancement algorithm, is optimized with the Hidden Markov Model and tested with 6660 medical speech transcription audio files and 1440 Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) audio files. The performance of the proposed model is compared with those of various typical speech enhancement algorithms, such as iterative signal enhancement algorithm, subspace-based speech enhancement, and non-linear spectral subtraction. The proposed cascaded hybrid algorithm was found to achieve a minimum word error rate of 9.5% and 7.6% for medical speech and RAVDESS speech, respectively. The cascading of the speech enhancement and speech-to-text conversion architectures results in higher accuracy for enhanced speech recognition. The evaluation results confirm the incorporation of the proposed method with real-time automatic speech recognition medical applications where the complexity of terms involved is high.

show abstract

“…It is also used in other application including speech processing, noise reduction, deblurring, etc. [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

VLSI Architectures of a Wiener Filter for Video Coding

et al. 2021

View full text Add to dashboard Cite

In the modern age, the use of video has become fundamental in communication and this has led to its use through an increasing number of devices. The higher resolution required for images and videos leads to more memory space and more efficient data compression, obtained by improving video coding techniques. For this reason, the Alliance for Open Media (AOMedia) developed a new open-source and royalty-free codec, named AOMedia Video 1 (AV1). This work focuses on the Wiener filter, a specific loop restoration tool of the AV1 video coding format, which features a significant amount of computational complexity. A new hardware architecture implementing the separable symmetric normalized Wiener filter is presented. Furthermore, the paper details possible optimizations starting from the basic architecture. These optimizations allow the Wiener filter to achieve a 100× reduction in processing time, compared to existing works, and 5× improvement in megasamples per second.

show abstract

Speech Enhancement for Secure Communication Using Coupled Spectral Subtraction and Wiener Filter

Cited by 9 publications

References 53 publications

Managing 5G Technology: Using Quality of Experience (QoE) to Identify the Innovation Enhancement Pattern According to the Indonesian Market

Managing 5G Technology: Using Quality of Experience (QoE) to Identify the Innovation Enhancement Pattern According to the Indonesian Market

A Hybrid Speech Enhancement Algorithm for Voice Assistance Application

VLSI Architectures of a Wiener Filter for Video Coding

Contact Info

Product

Resources

About