Results 81 to 90 of about 167,964,167 (121)

End-to-End Optimization of Source Models for Speech and Audio Coding Using a Machine Learning Framework

open access: yes, 2019
Speech coding is the most commonly used application of speech processing. Accumulated layers of improvements have however made codecs so complex that optimization of individual modules becomes increasingly difficult. This work introduces machine learning
Bäckström, Tom, Tom Bäckström
core   +1 more source

Addressing human speech characteristics in single-channel speaker extraction networks [PDF]

open access: yesPeerJ Computer Science
The objective of single-channel speaker extraction is to isolate the clean speech of a target speaker from a mixture of multiple speakers’ utterances. Conventionally, an auxiliary reference network is utilized to extract the speaker’s voiceprint features
Xinghuo Ye   +3 more
doaj   +2 more sources

Improvement of PESQ based on UVS classification and syllable stability detection

open access: yes, 2010
Hearing perception is different to speech segment, especially to unvoiced, voiced and silence (UVS) and it is also affected by the stability of frame distortions in each syllable.
Liu, Yi, Huang, Shilei, Wang, Jing
core   +1 more source

Perceptual Evaluation Of Speech Quality (pesq) -- A

open access: yes, 2001
Previous objective speech quality assessment models, such as bark spectral distortion (BSD), the perceptual speech quality measure (PSQM), and measuring normalizing blocks (MNB), have been found to be suitable for assessing only a limited range of ...
John G. Beerends   +4 more
core  

Speech Enhancement Network Based on Parallel Multi-Attention [PDF]

open access: yesJisuanji gongcheng
Regarding the issue of the frequency-domain enhancement of speech affected by interference, a speech enhancement network based on a parallel multi-attention mechanism and an encoding and decoding structure, known as PMAN, is proposed.
ZHANG Chi, WANG Zhong, JIANG Tianhao, XIE Kangmin
doaj   +1 more source

Deep causal speech enhancement and recognition using efficient long-short term memory Recurrent Neural Network.

open access: yesPLoS ONE
Long short-term memory (LSTM) has been effectively used to represent sequential data in recent years. However, LSTM still struggles with capturing the long-term temporal dependencies.
Zhenqing Li   +3 more
doaj   +1 more source

Research on objective speech quality measurements

open access: yes, 2001
Thesis (M.Eng. and S.B.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2001.Includes bibliographical references (p. 67-68).This is a thesis dissertation on objective speech quality measures.
Chow, Carol S., 1978-
core  

Artificial Intelligence Meets Your Voice: Transforming Turkish Text into Personalized Speech

open access: yesElectrica
Advancements in artificial intelligence (AI)-driven text-to-speech (TTS) technology have enabled transformative applications in accessibility and personalized learning.
Funda Akar
doaj   +1 more source

Quality aspects of Internet telephony [PDF]

open access: yes, 2009
Internet telephony has had a tremendous impact on how people communicate. Many now maintain contact using some form of Internet telephony. Therefore the motivation for this work has been to address the quality aspects of real-world Internet telephony ...
Marsh, Ian, Marsh, Ian R.
core  

Home - About - Disclaimer - Privacy