2017
DOI: 10.1109/taslp.2017.2738559
|View full text |Cite
|
Sign up to set email alerts
|

Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
20
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 58 publications
(20 citation statements)
references
References 21 publications
0
20
0
Order By: Relevance
“…They took into consideration a pronunciation model since words may have multiple correct pronunciations, as they are influenced by factors such as the speaker's accent, speaking style, and neighboring words. The authors of [55] presented vocal characteristics of whispered speech and discussed the problems for the recognition of whispered speech in different conditions. They provided a new pre-process method with cepstral features based on a deep denoising autoencoder (DDAE) to improve whisper recognition.…”
Section: ) Pronunciationmentioning
confidence: 99%
“…They took into consideration a pronunciation model since words may have multiple correct pronunciations, as they are influenced by factors such as the speaker's accent, speaking style, and neighboring words. The authors of [55] presented vocal characteristics of whispered speech and discussed the problems for the recognition of whispered speech in different conditions. They provided a new pre-process method with cepstral features based on a deep denoising autoencoder (DDAE) to improve whisper recognition.…”
Section: ) Pronunciationmentioning
confidence: 99%
“…In classification tasks, it is essential to obtain a set of features that helps to translate meaningful information accurately to discriminate the respective identities of the features [ 2 , 31 , 32 ]. In human speech recognition applications, extracted formant coefficients are often harvested and manipulated and then used as features [ 33 , 34 , 35 , 36 ]. Speech recognition processes in the present-day scenarios have reached a level of maturity where they are able to produce exceptional performance.…”
Section: Spectral Entropy Features and Classification Frameworkmentioning
confidence: 99%
“…Whispered speech is a method of articulation different from normal speech [1]; it is produced without vibration of the vocal cords at a low sound level, which causes the voiced sound of whispered speech to have no fundamental frequency and an energy 20 dB less than that of normal speech [2]. Because of these characteristics, whispered speech is widely used in places where loud noises are prohibited such as conference rooms, libraries, and concert halls.…”
Section: Introductionmentioning
confidence: 99%