AIMC Topic: Speech Acoustics

Clear Filters Showing 41 to 47 of 47 articles

Use of a Deep Recurrent Neural Network to Reduce Wind Noise: Effects on Judged Speech Intelligibility and Sound Quality.

Trends in hearing Jan 1, 2018
Despite great advances in hearing-aid technology, users still experience problems with noise in windy environments. The potential benefits of using a deep recurrent neural network (RNN) for reducing wind noise were assessed. The RNN was trained using...
Male Noise Acoustics Female Wind Young Adult Hearing Loss Speech Perception Speech Acoustics Auditory Threshold Random Allocation Speech Intelligibility Hearing Aids Humans Neural Networks, Computer
View on PubMed DOI

A transfer learning approach to goodness of pronunciation based automatic mispronunciation detection.

The Journal of the Acoustical Society of America Nov 1, 2017
Goodness of pronunciation (GOP) is the most widely used method for automatic mispronunciation detection. In this paper, a transfer learning approach to GOP based mispronunciation detection when applying maximum F1-score criterion (MFC) training to de...
Humans Software Deep Learning Phonetics Pattern Recognition, Automated Speech Acoustics Voice Quality Judgment Signal Processing, Computer-Assisted Speech Production Measurement Speech Perception Acoustics Markov Chains
View on PubMed DOI

Convolutional neural network-based automatic classification of midsagittal tongue gestural targets using B-mode ultrasound images.

The Journal of the Acoustical Society of America Jun 1, 2017
Tongue gestural target classification is of great interest to researchers in the speech production field. Recently, deep convolutional neural networks (CNN) have shown superiority to standard feature extraction techniques in a variety of domains. In ...
Signal Processing, Computer-Assisted Tongue Pattern Recognition, Automated Speech Acoustics Voice Quality Deep Learning Gestures Humans Ultrasonography Neural Networks, Computer Female Biomechanical Phenomena Male
View on PubMed DOI

Auditory feature representation using convolutional restricted Boltzmann machine and Teager energy operator for speech recognition.

The Journal of the Acoustical Society of America Jun 1, 2017
In this letter, authors propose an auditory feature representation technique with the filterbank learned using an annealing dropout convolutional restricted Boltzmann machine (ConvRBM) and noise-robust energy estimation using the Teager energy operat...
Signal Processing, Computer-Assisted Acoustics Sound Spectrography Neural Networks, Computer Machine Learning Time Factors Voice Quality Pattern Recognition, Automated Speech Acoustics Speech Production Measurement Humans
View on PubMed DOI

Estimating the spectral tilt of the glottal source from telephone speech using a deep neural network.

The Journal of the Acoustical Society of America Apr 1, 2017
Estimation of the spectral tilt of the glottal source has several applications in speech analysis and modification. However, direct estimation of the tilt from telephone speech is challenging due to vocal tract resonances and distortion caused by spe...
Humans Female Acoustics Speech Production Measurement Sound Spectrography Phonation Voice Quality Speech Acoustics Male Telephone Glottis Deep Learning Signal Processing, Computer-Assisted
View on PubMed DOI

Restoring speech following total removal of the larynx by a learned transformation from sensor data to acoustics.

The Journal of the Acoustical Society of America Mar 1, 2017
Total removal of the larynx may be required to treat laryngeal cancer: speech is lost. This article shows that it may be possible to restore speech by sensing movement of the remaining speech articulators and use machine learning algorithms to derive...
Transducers Lip Voice Quality Larynx, Artificial Machine Learning Speech Intelligibility Biomechanical Phenomena Time Factors Speech Acoustics Acoustics Recovery of Function Laryngectomy Humans Sound Spectrography Signal Processing, Computer-Assisted Prosthesis Design Magnets Tongue Magnetic Fields Magnetics
View on PubMed DOI

Improved speech inversion using general regression neural network.

The Journal of the Acoustical Society of America Sep 1, 2015
The problem of nonlinear acoustic to articulatory inversion mapping is investigated in the feature space using two models, the deep belief network (DBN) which is the state-of-the-art, and the general regression neural network (GRNN). The task is to e...
Speech Production Measurement Male Numerical Analysis, Computer-Assisted Regression Analysis Humans Pattern Recognition, Automated Computer Simulation Nonlinear Dynamics Neural Networks, Computer Phonetics Female Databases, Factual Speech Acoustics Reproducibility of Results
View on PubMed DOI
Popular Topics
Recent Journals