from #Audiology via ola Kala on Inoreader https://ift.tt/2osQTuc
via IFTTT
OtoRhinoLaryngology by Sfakianakis G.Alexandros Sfakianakis G.Alexandros,Anapafseos 5 Agios Nikolaos 72100 Crete Greece,tel : 00302841026182,00306932607174
Publication date: Available online 31 August 2018
Source: Hearing Research
Author(s): Dongshu Wang, Hui Shan, Jianbin Xin
Compared with machine audition, the human auditory system can recognize speech accurately and quickly. This paper proposes a new developmental network (DN) that simulates the human auditory system and constructs an artificial auditory model for speech recognition. The new model simulates each key element of the human auditory pathway as a deep network; in particular, an additional layer in the network is considered to simulate the function of the superior colliculus in the thalamus for speech context integration. The mel-frequency cepstral coefficient (MFCC) is used to extract the features of the speech signal as the sensory input of the DN. The emergent feature of DN model provides an explanation of how such internal neurons represent the short speech context when they are not supervised by the external world. The experimental results show that the recognition rates of English words and phrases can be improved significantly compared to those reported in the existing literature. The proposed DN model provides a new method to solve difficult problems, such as universal speech recognition, in traditional machine audition systems. Meanwhile, the same learning principle can potentially be used in or adapted to other computational contexts and applications.
Publication date: Available online 31 August 2018
Source: Hearing Research
Author(s): Dongshu Wang, Hui Shan, Jianbin Xin
Compared with machine audition, the human auditory system can recognize speech accurately and quickly. This paper proposes a new developmental network (DN) that simulates the human auditory system and constructs an artificial auditory model for speech recognition. The new model simulates each key element of the human auditory pathway as a deep network; in particular, an additional layer in the network is considered to simulate the function of the superior colliculus in the thalamus for speech context integration. The mel-frequency cepstral coefficient (MFCC) is used to extract the features of the speech signal as the sensory input of the DN. The emergent feature of DN model provides an explanation of how such internal neurons represent the short speech context when they are not supervised by the external world. The experimental results show that the recognition rates of English words and phrases can be improved significantly compared to those reported in the existing literature. The proposed DN model provides a new method to solve difficult problems, such as universal speech recognition, in traditional machine audition systems. Meanwhile, the same learning principle can potentially be used in or adapted to other computational contexts and applications.
Related Articles |
Unusual discovery of a vestibular schwannoma following eradication therapy for Mycobacterium abscessus.
BMJ Case Rep. 2018 Aug 29;2018:
Authors: Wilson C, Duckers J, Rajenderkumar D
Abstract
A young man with cystic fibrosis in his early 30s presented to accident and emergency with acute onset unilateral lower motor neuron facial palsy, hearing loss and impaired balance following Mycobacterium abscessus eradication induction therapy. The hearing loss and impaired balance developed over a 3-day period prior to the onset of facial palsy. Further investigation with a CT scan and MRI scan led to a diagnosis of vestibular schwannoma. The facial palsy resolved with steroid treatment; however, the hearing loss is irreversible, which has had a profound impact on his life and career. This case is intriguing as the cause and association of events are unclear. A working diagnosis of incidental Bell's palsy and unilateral hearing loss caused by the vestibular schwannoma was applied. However, the onset of these symptoms in relation to M. abscessus eradication induction therapy promotes discussion.
PMID: 30158267 [PubMed - in process]
Related Articles |
Unusual discovery of a vestibular schwannoma following eradication therapy for Mycobacterium abscessus.
BMJ Case Rep. 2018 Aug 29;2018:
Authors: Wilson C, Duckers J, Rajenderkumar D
Abstract
A young man with cystic fibrosis in his early 30s presented to accident and emergency with acute onset unilateral lower motor neuron facial palsy, hearing loss and impaired balance following Mycobacterium abscessus eradication induction therapy. The hearing loss and impaired balance developed over a 3-day period prior to the onset of facial palsy. Further investigation with a CT scan and MRI scan led to a diagnosis of vestibular schwannoma. The facial palsy resolved with steroid treatment; however, the hearing loss is irreversible, which has had a profound impact on his life and career. This case is intriguing as the cause and association of events are unclear. A working diagnosis of incidental Bell's palsy and unilateral hearing loss caused by the vestibular schwannoma was applied. However, the onset of these symptoms in relation to M. abscessus eradication induction therapy promotes discussion.
PMID: 30158267 [PubMed - in process]