Bibliographic record
Abstract
Speech enhancement has been extensively studied for many years and various speech enhance- ment methods have been developed during the past decades. One of the objectives of speech en- hancement is to provide high-quality speech communication in the presence of background noise and concurrent interference signals. In the process of speech communication, the clean speech sig- nal is inevitably corrupted by acoustic noise from the surrounding environment, transmission media, communication equipment, electrical noise, other speakers, and other sources of interference. These disturbances can significantly degrade the quality and intelligibility of the received speech signal. Therefore, it is of great interest to develop efficient speech enhancement techniques to recover the original speech from the noisy observation. In recent years, various techniques have been developed to tackle this problem, which can be classified into single channel and multi-channel enhancement approaches. Since single channel enhancement is easy to implement, it has been a significant field of research and various approaches have been developed. For example, spectral subtraction and Wiener filtering, are among the earliest single channel methods, which are based on estimation of the power spectrum of stationary noise. However, when the noise is non-stationary, or there exists music noise and ambient speech noise, the enhancement performance would degrade considerably. To overcome this disadvantage, this thesis focuses on single channel speech enhancement under adverse noise environment, especially the non-stationary noise environment. \nRecently, wavelet transform based methods have been widely used to reduce the undesired background noise. On the other hand, the Kalman filter (KF) methods offer competitive denoising results, especially in non-stationary environment. It has been used as a popular and powerful tool for speech enhancement during the past decades. In this regard, a single channel wavelet thresholding based Kalman filter (KF) algorithm is proposed for speech enhancement in this thesis. The wavelet packet (WP) transform is first applied to the noise corrupted speech on a frame-by-frame basis, which decomposes each frame into a number of subbands. A voice activity detector (VAD) is then designed to detect the voiced/unvoiced frames of the subband speech. Based on the VAD result, an adaptive thresholding scheme is applied to each subband speech followed by the WP based reconstruction to obtain the pre-enhanced speech. To achieve a further level of enhancement, an iterative Kalman filter (IKF) is used to process the pre-enhanced speech. \nThe proposed adaptive thresholding iterative Kalman filtering (AT-IKF) method is evaluated and compared with some existing methods under various noise conditions in terms of segmental SNR and perceptual evaluation of speech quality (PESQ) as two well-known performance indexes. Firstly, we compare the proposed adaptive thresholding (AT) scheme with three other threshold- ing schemes: the non-linear universal thresholding (U-T), the non-linear wavelet packet transform thresholding (WPT-T) and the non-linear SURE thresholding (SURE-T). The experimental results show that the proposed AT scheme can significantly improve the segmental SNR and PESQ for all input SNRs compared with the other existing thresholding schemes. Secondly, extensive computer simulations are conducted to evaluate the proposed AT-IKF as opposed to the AT and the IKF as standalone speech enhancement methods. It is shown that the AT-IKF method still performs the best. Lastly, the proposed ATIKF method is compared with three representative and popular meth- ods: the improved spectral subtraction based speech enhancement algorithm (ISS), the improved Wiener filter based method (IWF) and the representative subband Kalman filter based algorithm (SIKF). Experimental results demonstrate the effectiveness of the proposed method as compared to some previous works both in terms of segmental SNR and PESQ.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".