Whispered speech recognition using deep denoising autoencoder

Grozdic, Dorde T.; Jovičić, Slobodan; Subotić, Miško

doi:10.1016/j.engappai.2016.12.012

Cited by 64 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of such areas are speech and speaker recognition. MFCCs have proven to outperform other coefficients in the two areas and they have shown to grant a high-level approximation of human auditory perception [17], [26], [27], [28]. In this study, a 32-dimension feature analysis of MFCCs (16 static MFCCs and 16 delta MFCCs) was utilized to found the observation vectors in each of "CSPHMM1s, CSPHMM2s, and CSPHMM3s".…”

Section: Extraction Of Featuresmentioning

confidence: 99%

Emirati-accented speaker identification in each of neutral and shouted talking environments

Shahin

Nassif

Bahutair

2018

Int J Speech Technol

View full text Add to dashboard Cite

This work is devoted to capturing Emirati-accented speech database (Arabic United Arab Emirates database) in each of neutral and shouted talking environments in order to study and enhance text-independent Emirati-accented "speaker identification performance in shouted environment" based on each of "First-Order Circular Suprasegmental Hidden Markov Models (CSPHMM1s), Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s), and Third-Order Circular Suprasegmental Hidden Markov Models (CSPHMM3s)" as classifiers.In this research, our database was collected from fifty Emirati native speakers (twenty five per gender) uttering eight common Emirati sentences in each of neutral and shouted talking environments. The extracted features of our collected database are called "Mel-Frequency Cepstral Coefficients (MFCCs)". Our results show that average Emirati-accented speaker identification performance in neutral environment is 94.0%, 95.2%, and 95.9% based on CSPHMM1s, CSPHMM2s, and CSPHMM3s, respectively. On the other hand, the average performance in shouted environment is 51.3%, 55.5%, and 59.3% based, respectively, on "CSPHMM1s, CSPHMM2s, and CSPHMM3s". The achieved "average speaker identification performance in shouted environment based on CSPHMM3s" is very similar to that obtained in "subjective assessment by human listeners". 2

show abstract

Section: Extraction Of Featuresmentioning

confidence: 99%

Emirati-accented speaker identification in each of neutral and shouted talking environments

Shahin

Nassif

Bahutair

2018

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

“…The use of Teager energy cepstral coefficients with deep denoising autoencoder (DDA) has recently brought many benefits in speaker dependent (SD) neutraltrained whisper recognition [18]. Likewise, performances of speaker independent (SI) recognition of whispered speech have been significantly improved after adapting the acoustic model toward the DDA pseudo-whisper samples, compared to the model adaptation on an available small whisper set (for UT-Vocal Effort II speech corpus) [13,15].…”

Section: Related Workmentioning

confidence: 99%

Whispered Speech Recognition using Hidden Markov Models and Support Vector Machines

2018

APH

View full text Add to dashboard Cite

Whisper is a specific mode of speech characterized by turbulent airflow at the glottis level. Despite an increased effort in speech perception, the intelligibility of whisper in human communication is very high. An enormous acoustic mismatch between normally phonated (neutral) and whispered speech is the main reason why modern Automatic Speech Recognition (ASR) systems have significant drop of performances when applied to whisper. In this paper, we present an analysis in recognition of whisper using 2 machinelearning techniques: Hidden Markov Models (HMM) and Support Vector Machines (SVM). The experiments are conducted in both Speaker Dependent (SD) and Speaker Independent (SI) fashion for Whi-Spe speech database. The best neutral-trained whisper recognition accuracy in SD fashion (83.36%) is obtained in SVM framework. At the same time, HMMbased recognition gave the highest recognition accuracy in SI fashion (87.42%). The results in recognition of neutral speech are given as well.

show abstract

“…DNN is superior to other conventional neural networks in the classification problem with the help of the aforementioned properties by having complex decision surface. 6,7,[22][23][24][25][26][27][28][29]…”

Section: Introductionmentioning

confidence: 99%

Type 2 diabetes data classification using stacked autoencoders in deep neural networks

Kannadasan

Edla

Kuppili

2019

Clinical Epidemiology and Global Health

126

View full text Add to dashboard Cite

This paper aims to classify the Pima Indians diabetes dataset with better accuracy and other evaluation metrics. The Deep Neural Network (DNN) framework will help to diagnose the patient in an effective way with higher accuracy. Method: In this approach, we proposed a Deep Neural Network framework for diabetes data classification using stacked autoencoders. Features are extracted from the dataset using stacked autoencoders and the dataset is classified using softmax layer. Also, fine tuning of the network is done using backpropagation in supervised fashion with the training dataset. However, the medical diagnosis involves the risk factors of wrong prediction; hence we have used evaluation metrics such as precision, recall, specificity and F1-score for the evaluation of our model and have achieved better results. Results: The proposed framework is experimented on Pima Indians Diabetes data which has 768 patient records with 8 attributes for each record. We achieved classification accuracy of 86.26%. Conclusion: A stacked autoencoders based Deep Learning framework for classification of Type 2 Diabetes data is proposed in this paper. This approach is experimented on UCI machine learning data and proved the outperformance over various existing classification methods.

show abstract

Whispered speech recognition using deep denoising autoencoder

Cited by 64 publications

References 33 publications

Emirati-accented speaker identification in each of neutral and shouted talking environments

Emirati-accented speaker identification in each of neutral and shouted talking environments

Whispered Speech Recognition using Hidden Markov Models and Support Vector Machines

Type 2 diabetes data classification using stacked autoencoders in deep neural networks

Contact Info

Product

Resources

About