Results 31 to 40 of about 3,919,398 (308)

Coarticulation vs Phonologization: Evidence from Southern Italo-Romance [PDF]

JASA Express Letters
This study compares the variety of Italian spoken in Campania and the Italo-Romance variety of Mormanno (Calabria) to investigate the acoustic differences between phonetic vowel-to-vowel coarticulation and phonologized metaphony.
Pia Greca, Francesco Burroni, Jonathan Harrington   +2 more
doaj   +1 more source

Elastic CRFs for Open-Ontology Slot Filling

Applied Sciences, 2021
Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take.
Yinpei Dai, Yichi Zhang, Hong Liu, Zhijian Ou, Yi Huang, Junlan Feng   +5 more
doaj   +1 more source

Introduction to Digital Speech Processing [PDF]

Foundations and Trends® in Signal Processing, 2007
Since even before the time of Alexander Graham Bell’s revolutionary invention, engineers and scientists have studied the phenomenon of speech communication with an eye on creating more efficient and effective systems of human-to-human and human-to-machine communication.
Lawrence R. Rabiner, Ronald W. Schafer
openaire   +1 more source

Overlap-add Windows with Maximum Energy Concentration for Speech and Audio Processing

, 2019
Processing of speech and audio signals with time-frequency representations require windowing methods which allow perfect reconstruction of the original signal and where processing artifacts have a predictable behavior.
Bäckström, T., Tom Backstrom
core   +1 more source

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction [PDF]

, 2010
This paper demonstrates how unsupervised cross-lingual adaptation of HMM-based speech synthesis models may be performed without explicit knowledge of the adaptation data language.
Teemu Hirsimaki, Mikko Kurimo, Reima Karhila, Matthew Gibson, William Byrne, Karhila, Reima   +5 more
core   +2 more sources

iCUS: Intelligent CU Size Selection for HEVC Inter Prediction

IEEE Access, 2020
The hierarchical quadtree partitioning of Coding Tree Units (CTU) is one of the striking features in HEVC that contributes towards its superior coding performance over its predecessors.
Buddhiprabha Erabadda, Thanuja Mallikarachchi, Gosala Kulupana, Anil Fernando   +3 more
doaj   +1 more source

Audio Inpainting [PDF]

, 2012
(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or ...
Emiya, Valentin, Maria G. Jafari, Emiya, V, Gribonval, R, Plumbley, MD, Amir Adler, Michael Elad, Mark D. Plumbley, Adler, Amir, Elad, M, Gribonval, Rémi, Plumbley, Mark D., Rémi Gribonval, Jafari, MG, Jafari, Maria, G., Elad, Michael, Adler, A, Valentin Emiya   +17 more
core   +1 more source

A Formant Modification Method for Improved ASR of Children’s Speech

, 2022
Differences in acoustic characteristics between children’s and adults’ speech degrade performance of automatic speech recognition systems when systems trained using adults’ speech are used to recognize children’s speech.
Alku, Paavo, Kurimo, Mikko, Kadiri, Sudarsana, Kathania, Hemant, Sudarsana Reddy Kadiri, Paavo Alku, Mikko Kurimo, Hemant Kumar Kathania   +7 more
core   +1 more source

Effective Exploitation of Posterior Information for Attention-Based Speech Recognition

IEEE Access, 2020
End-to-end attention-based modeling is increasingly popular for tackling sequence-to-sequence mapping tasks. Traditional attention mechanisms utilize prior input information to derive attention, which then conditions the output.
Jian Tang, Junfeng Hou, Yan Song, Li-Rong Dai, Ian Mcloughlin   +4 more
doaj   +1 more source

Packet Loss Concealment Based on Phase Correction and Deep Neural Network

Applied Sciences, 2022
In a packet switching network, the performance of packet loss concealment (PLC) is often affected by inaccurate estimation of phase spectrum of speech signal in the lost packet.
Qiang Ji, Changchun Bao, Zihao Cui
doaj   +1 more source