Speech enhancement based on audible noise suppression

Tsoukalas, Dionysis E.; Mourjopoulos, John; Kokkinakis, G.

doi:10.1109/89.641296

Cited by 145 publications

(77 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the nonlinear method shows that, noise signal does not affect the speech signal uniformly over the whole spectrum because certain frequencies are affected more adversely than others [21], [22]. To prevent the variation of signal-to-noise ratio across the enhanced speech spectrum as well as destructive subtraction of speech while removing most of the residual noise, it is necessary to develop an appropriate scheme that will subtract only the necessary amount of noise spectrum from each frequency bin [7], [8].…”

Section: A Speech Enhancementmentioning

confidence: 99%

Performance Improvement of Digital Hearing Aid Systems

Alimi

2015

JCTECS

View full text Add to dashboard Cite

Abstract-Digital hearing aids addresses the issues of noise and speech intelligibility that is associated with the analogue types. One of the main functions of the digital signal processor (DSP) of digital hearing aid systems is noise reduction which can be achieved by speech enhancement algorithms which in turn improve system performance and flexibility. However, studies have shown that the quality of experience (QoE) with some of the current hearing aids is not up to expectation in a noisy environment due to interfering sound, background noise and reverberation. It is also suggested that noise reduction features of the DSP can be further improved accordingly. Recently, we proposed an adaptive spectral subtraction algorithm to enhance the performance of communication systems and address the issue of associated musical noise generated by the conventional spectral subtraction algorithm. The effectiveness of the algorithm has been confirmed by different objective and subjective evaluations. In this study, an adaptive spectral subtraction algorithm is implemented using the noise-estimation algorithm for highly non-stationary noisy environments instead of the voice activity detection (VAD) employed in our previous work due to its effectiveness. Also, signal to residual spectrum ratio (SR) is implemented in order to control the amplification distortion for speech intelligibility improvement. The results show that the proposed scheme gives comparatively better performance and can be easily employed in digital hearing aid system for improving speech quality and intelligibility.

show abstract

Section: A Speech Enhancementmentioning

confidence: 99%

Performance Improvement of Digital Hearing Aid Systems

Alimi

2015

JCTECS

View full text Add to dashboard Cite

show abstract

“…However, the underlying speech should not be affected. Such systems have been used successfully in [28,29,69] for speech enhancement.…”

Section: Motivation For the Perceptual Post-filtermentioning

confidence: 99%

Signal subspace speech enhancement with perceptual post-filtering

Klein

Kabal

2002

IEEE International Conference on Acoustics Speech and Signal Processing

View full text Add to dashboard Cite

“…Therefore we adopt a more sophisticated speech enhancement algorithm proposed by Chen et al (2007), which is based on the masking properties and short-time spectral amplitude estimation. Masking properties of human auditory system were first introduced by Johnston (1988) and later used in the speech enhancement by Tsoukalas et al (1997) and Virag (1999). Generally speaking the speech signal is the stronger signal than the background noise is the weaker signal.…”

Section: Speech Enhancement Based On Masking Propertiesmentioning

confidence: 99%

Speech Emotion Recognition under White Noise

Huang¹,

Chen²,

Yu³

et al. 2013

Archives of Acoustics

View full text Add to dashboard Cite

Speaker's emotional states are recognized from speech signal with Additive white Gaussian noise (AWGN). The influence of white noise on a typical emotion recogniztion system is studied. The emotion classifier is implemented with Gaussian mixture model (GMM). A Chinese speech emotion database is used for training and testing, which includes nine emotion classes (e.g. happiness, sadness, anger, surprise, fear, anxiety, hesitation, confidence and neutral state). Two speech enhancement algorithms are introduced for improved emotion classification. In the experiments, the Gaussian mixture model is trained on the clean speech data, while tested under AWGN with various signal to noise ratios (SNRs). The emotion class model and the dimension space model are both adopted for the evaluation of the emotion recognition system. Regarding the emotion class model, the nine emotion classes are classified. Considering the dimension space model, the arousal dimension and the valence dimension are classified into positive regions or negative regions. The experimental results show that the speech enhancement algorithms constantly improve the performance of our emotion recognition system under various SNRs, and the positive emotions are more likely to be miss-classified as negative emotions under white noise environment.

show abstract

Speech enhancement based on audible noise suppression

Cited by 145 publications

References 24 publications

Performance Improvement of Digital Hearing Aid Systems

Performance Improvement of Digital Hearing Aid Systems

Signal subspace speech enhancement with perceptual post-filtering

Speech Emotion Recognition under White Noise

Contact Info

Product

Resources

About