Wide matching — An approach to improving noise robustness for speech enhancement

Ji, Ming; Crookes, Danny

doi:10.1109/icassp.2016.7472811

Cited by 2 publications

(4 citation statements)

References 25 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, we propose an efficient implementation to put the new method into practical use. This paper is a substantial expansion of our preliminary study described in [51]. The expansions include an expanded theoretical study, an efficient implementation algorithm for speech enhancement, and extensive experimental investigations across two different databases.…”

Section: Introductionmentioning

confidence: 99%

Speech Enhancement Based on Full-Sentence Correlation and Clean Speech Recognition

Crookes

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

Conventional speech enhancement methods, based on frame, multi-frame or segment estimation, require knowledge about the noise. This paper presents a new method which aims to reduce or effectively remove this requirement. It is shown that, by using the Zero-mean Normalized Correlation Coefficient (ZNCC) as the comparison measure, and by extending the effective length of speech segment matching to sentencelong speech utterances, it is possible to obtain an accurate speech estimate from noise without requiring specific knowledge about the noise. The new method, thus, could be used to deal with unpredictable noise or noise without proper training data. This paper is focused on realizing and evaluating this potential. We propose a novel realization that integrates full-sentence speech correlation with clean speech recognition, formulated as a constrained maximization problem, to overcome the data sparsity problem. Then we propose an efficient implementation algorithm to solve this constrained maximization problem, to produce speech sentence estimates. For evaluation, we build the new system on one training data set and test it on two different test data sets across two databases, for a range of different noises including highly nonstationary ones. It is shown that the new approach, without any estimation of the noise, is able to significantly outperform conventional methods which use optimized noise tracking, in terms of various objective measures including automatic speech recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

Speech Enhancement Based on Full-Sentence Correlation and Clean Speech Recognition

Crookes

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have attempted in this paper to improve speech enhancement performance by exploiting ASR technology. Similar attempts have been made in some other studies [14,24,25] and we can refer to them to further improve our method.…”

Section: Relation To Previous Workmentioning

confidence: 60%

“…that jointly performs HMM state prediction and speaker identification (i.e. a multitask learning [39]), and (3) more tight integration with the ASR technology [14,24,25] for complementarily improving the performance of speech enhancement and ASR.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Example-Based Speech Enhancement by Using Deep Neural Network Acoustic Model for Noise Robust Example Search

et al. 2017

View full text Add to dashboard Cite

Example-based speech enhancement is a promising singlechannel approach for coping with highly nonstationary noise. Given a noisy speech input, it first searches in a noisy speech corpus for the noisy speech examples that best match the input. Then, it concatenates the clean speech examples that are paired with the matched noisy examples to obtain an estimate of the underlying clean speech component in the input. The quality of the enhanced speech depends on how accurate an example search can be performed given a noisy speech input. The example search is conventionally performed using a Gaussian mixture model (GMM) with mel-frequency cepstral coefficient features (MFCCs). To improve the noise robustness of the GMM-based example search, instead of using noise sensitive MFCCs, we have proposed using bottleneck features (BNFs), which are extracted from a deep neural network-based acoustic model (DNN-AM) built for automatic speech recognition. In this paper, instead of using a GMM with noise robust BNFs, we propose the direct use of a DNN-AM in the example search to further improve its noise robustness. Experimental results on the Aurora4 corpus show that the DNN-AM-based example search steadily improves the enhanced speech quality compared with the GMM-based example search using BNFs. Index Terms: example-based speech enhancement, example search, noise robustness, deep neural network acoustic model

show abstract

Wide matching — An approach to improving noise robustness for speech enhancement

Cited by 2 publications

References 25 publications

Speech Enhancement Based on Full-Sentence Correlation and Clean Speech Recognition

Speech Enhancement Based on Full-Sentence Correlation and Clean Speech Recognition

Improved Example-Based Speech Enhancement by Using Deep Neural Network Acoustic Model for Noise Robust Example Search

Contact Info

Product

Resources

About