Quality improvement of bone-conducted speech

Shinamura, T.; Tomikura, T.

doi:10.1109/ecctd.2005.1523063

Cited by 10 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned before, a BCM records signals through bone vibrations and is thus less sensitive to air background noise in comparison with an ACM. However, the BCM-recorded speech signals often suffer from a loss of high acoustic-frequency components, and this issue was addressed and partially alleviated through the BCM-to-ACM conversion technique applied in tasks [18,19].…”

Section: Bcm/acm Conversionmentioning

confidence: 99%

See 1 more Smart Citation

Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement

Hung

Wang

et al. 2020

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Integrating modalities, such as video signals with speech, has been shown to provide a standard quality and intelligibility for speech enhancement (SE). However, video clips usually contain large amounts of data and pose a high cost in terms of computational resources, which may complicate the respective SE. By contrast, a bone-conducted speech signal has a moderate data size while it manifests speech-phoneme structures, and thus complements its air-conducted counterpart, benefiting the enhancement. In this study, we propose a novel multi-modal SE structure that leverages bone-and air-conducted signals. In addition, we examine two strategies, early fusion and late fusion (LF), to process the two types of speech signals, and adopt a deep learning-based fully convolutional network to conduct the enhancement. The experiment results indicate that this newly presented multimodal structure significantly outperforms the single-source SE counterparts (with a bone-or air-conducted signal only) in various speech evaluation metrics. In addition, the adoption of an LF strategy other than an EF in this novel SE multi-modal structure achieves better results.

show abstract

Section: Bcm/acm Conversionmentioning

confidence: 99%

“…al. [18] used a reconstruction filter, which is designed using the long-term spectra of the speech, to perform the conversion. Meanwhile, numerous approaches have been proposed to combine ACM-and BCM-recorded sound in hardware devices with a linear transformation for SE and speech recognition tasks [19,20].…”

Section: Introductionmentioning

confidence: 99%

Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement

Hung

Wang

et al. 2020

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…According to Shimamura et al [2], by passing speaker output of bone conducted speech signal a long term spectra reconstructed filter design, the arena of bone conducted and reconstructed speech from normal signal could be highly utilized. By passing normal speech signal through linear process with a transfer function of bone conduction can be obtained, to identify the properties of numerous sounds, spectral shapes by removing the dissimilarities.…”

Section: Brief Review On Approachesmentioning

confidence: 99%

A Study to Analyze Enhancement Techniques on Sound Quality for Bone Conduction and Air Conduction Speech Processing

Subbaiah

Deepthi

2020

SCPE

View full text Add to dashboard Cite

In recent years, enhancing speech signal for communications become more complex due to the environmental noises for military and navel applications. Many researchers analyzed and developed complex algorithms and expressed ways to enhance speech signal for both Bone Conducted Speech (BCS) and Air Conducted Speech (ACS) processing techniques. BCS signal is vigorous for outer environmental noises and with low quality signal. ACS signal is sensitive for environmental noises nut rigid in amplitude and high frequencies.Here we have reviewed and investigated various articles to explore their ideas in speech processing for enhancing intelligibility of sound quality.

show abstract

“…As a speaker-dependent technique, the use of an air-and bone-conduction integrated microphone is suggested in [6]. In [7], it is reported that the quality of bone-conducted speech can be improved by utilizing both longterm spectra of the normal and bone-conducted speech signals.…”

Section: Introductionmentioning

confidence: 99%

Improving Bone-Conducted Speech Quality via Neural Network

Shimamura

Mamiya

Tamiya

2006

2006 IEEE International Symposium on Signal Processing and Information Technology

View full text Add to dashboard Cite

The quality of bone-conducted speech is low, but bone-conducted speech itself is not affected by noise. In this paper, we take into account such properties of bone-conducted speech, and derive a reconstruction filter to improve the quality of bone-conducted speech. The reconstruction filter is designed by learning a neural network on the basis of the bone-conducted speech and normal speech obtained from a speaker. Experimental results show that the reconstructed speech signal has better quality than the bone-conducted speech signal.

show abstract

Quality improvement of bone-conducted speech

Cited by 10 publications

References 2 publications

Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement

Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement

A Study to Analyze Enhancement Techniques on Sound Quality for Bone Conduction and Air Conduction Speech Processing

Improving Bone-Conducted Speech Quality via Neural Network

Contact Info

Product

Resources

About