AIMC Topic: Sound Spectrography

Clear Filters Showing 71 to 74 of 74 articles

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...
Humans Machine Learning Recovery of Function Signal Processing, Computer-Assisted Biomechanical Phenomena Time Factors Speech Acoustics Laryngectomy Speech Intelligibility Voice Quality Larynx, Artificial Transducers Lip Tongue Magnets Magnetic Fields Magnetics Acoustics Prosthesis Design Sound Spectrography
View on PubMed DOI

Speaker-dependent multipitch tracking using deep neural networks.

The Journal of the Acoustical Society of America Feb 1, 2017
Multipitch tracking is important for speech and signal processing. However, it is challenging to design an algorithm that achieves accurate pitch estimation and correct speaker assignment at the same time. In this paper, deep neural networks (DNNs) a...
Pitch Discrimination Models, Theoretical Signal Processing, Computer-Assisted Sound Spectrography Speech Perception Humans Male Neural Networks, Computer Speech Algorithms Female
View on PubMed DOI

Automatic Wheezing Detection Based on Signal Processing of Spectrogram and Back-Propagation Neural Network.

Journal of healthcare engineering Jan 1, 2015
Wheezing is a common clinical symptom in patients with obstructive pulmonary diseases such as asthma. Automatic wheezing detection offers an objective and accurate means for identifying wheezing lung sounds, helping physicians in the diagnosis, long-...
Adult Asthma Middle Aged Case-Control Studies Neural Networks, Computer Algorithms Humans Respiratory Sounds Signal Processing, Computer-Assisted Sound Spectrography Diagnosis, Computer-Assisted
View on PubMed DOI

Compensating for the effects of site and equipment variation on delphinid species identification from their echolocation clicks.

The Journal of the Acoustical Society of America Jan 1, 2015
A concern for applications of machine learning techniques to bioacoustics is whether or not classifiers learn the categories for which they were trained. Unfortunately, information such as characteristics of specific recording equipment or noise envi...
Pacific Ocean Normal Distribution Monte Carlo Method Transducers Sound Spectrography Machine Learning Pattern Recognition, Automated Algorithms Fourier Analysis Echolocation Species Specificity Animals Dolphins Subtraction Technique
View on PubMed DOI
Popular Topics
Recent Journals