Results 81 to 90 of about 27,627 (230)

Low-noise sound masking method using active noise control and spectral flattening

Nihon Kikai Gakkai ronbunshu, 2018
Sound masking is a method that used for protecting speech privacy of conversation at public open space such as a pharmacy or a bank window. In a conventional masking, a masking sound is used to cover contents of conversation.
Daichi YAMASHITA, Yosuke KOBA, Satoshi ISHIKAWA, Shinya KIJIMOTO   +3 more
doaj   +1 more source

Predicting formant frequencies from MFCC vectors

, 2005
This work proposes a novel method of predicting formant frequencies from a stream of mel-frequency cepstral coefficients (MFCC) feature vectors. Prediction is based on modelling the joint density of MFCCs and formant frequencies using a Gaussian mixture ...
Saeed Vaseghi, J. Darch, S. Vaseghi, Darch, Jonathan, Vaseghi, Saeed, Yan, Qin, Milner, Ben, Jonathan Darch, Xu Shao, Shao, Xu, Ben Milner, B. Milner, Qin Yan   +12 more
core   +1 more source

The Restructuring of Christian Personal Names in the Pre-National Period: Names ending in -a, -ija (-‘ja) [PDF]

Вопросы ономастики, 2013
The article opens a series of publications analyzing the derivation within a regional system of Christian personal name forms in the Pre-National period. With reference to the anthroponyms recorded in 16-17th centuries Tver business documents, the author
Irina M. Ganzhina
doaj  

Formant tracking using segmental phonemic information

, 1999
A new formant tracking algorithm using phoneme dependent nominal formant values is tested. The algorithm consists of three phases: (1) analysis, (2) segmentation, and (3) formant tracking. In the analysis phase, formant candidates are obtained by solving
Bernd Möbius, Joseph Olive, Minkyu Lee, Jan Van Santen   +3 more
core  

СЛОВОТВІРНА ПРОДУКТИВНІСТЬ ПРЕФІКСІВ ЗІ ЗНАЧЕННЯМ ПРОТИЛЕЖНОСТІ У ФОРМУВАННІ МЕДИЧНИХ ТЕРМІНІВ ТА ТЕРМІНОЛОГІЗОВАНИХ СЛІВ / Word-building productivity of prefixes with the meaning of opposition in the formation of medical and terminological words

Актуальні питання суспільних наук та історії медицини, 2015
Ткач Алла. Словообразовательная производительность приставок со значением противоположности в формировании медицинских терминов и терминологических слов.
Ткач Алла
doaj  

Jak badać samogłoski metodami akustycznymi? Propozycja metody opartej na względnych częstotliwościach formantowych oraz modelu samogłosek podstawowych

LingVaria, 2015
How to study vowels using acoustic methods? A proposal of a method based on relative formant frequencies and cardinal vowels model. Part II . The second part of the paper consists of a list of relative formant frequencies of model vowels (the method ...
Piotr Rybka
doaj   +1 more source

Robust formant analysis

, 1986
For speech synthesis applications a formant description of the speech signal has a number of advantages over oUter parametrizatiolls. The analysis of formant frequencies and bandwidths from the LPC coefficients has two drawbacks: sometimes the number of ...
Willems, LF Lei, Willems, L.F.
core  

Evaluation of Formant-Like Features for ASR [PDF]

This paper investigates possibilities to automatically find a low-dimensional, formant-related physical representation of the speech signal, which is suitable for automatic speech recognition (ASR).
Boves, Louis, de Wet, F., Cranen, B., Bourlard, Hervé, Bengio, Samy, Weber, Katrin   +5 more
core   +1 more source

Bio-inspired broad-class phonetic labelling

, 2008
Recent studies have shown that the correct labeling of phonetic classes may help current Automatic Speech Recognition (ASR) when combined with classical parsing automata based on Hidden Markov Models (HMM).Through the present paper a method for Phonetic ...
Martínez Olalla, Rafael, Rodellar Biarge, M. Victoria, Gómez Vilda, Pedro, Muñoz, Cristina, Fernández, L.M., Ferrández Vicente, José Manuel, Álvarez Marquina, Agustin   +6 more
core  

Adaptation to formant and fundamental frequencies.

, 2013
(A) Aftereffects induced with the fundamental frequency adaptor (f0A/formantAB). Right panel: statistical analysis, differences between each adaptation condition and baseline (i.e., no adaptation). Shaded area: 95% confidence interval.
Marianne Latinus (314936), Pascal Belin (314939)   +1 more
core   +1 more source