Results 71 to 80 of about 31,024 (224)
Acoustic-Phonetic Unit Similarities For Context Dependent Acoustic Model Portability [PDF]
2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006 This paper addresses particularly the use of acoustic-phonetic unit similarities for portability of context dependent acoustic models to new languages. Since the IPA-based method is limited to a source/target phoneme mapping table construction, an estimation method of the similarity between two phonemes is proposed in this paper. Based on these phoneme
Le, Viet-Bac +2 more
openaire +3 more sources
Postalveolar fricatives in Slavic languages as retroflexes [PDF]
, 2002 The present study poses the question on what phonetic and phonological grounds postalveolar fricatives in Polish can be analyzed as retroflex and whether postalveolar fricatives in other Slavic languages are retroflex as well.
Hamann, Silke
core
Inter‐Model Feature Fusion for Robust Low‐Resource Speech Recognition
Applied AI Letters, Volume 7, Issue 2, June 2026.Our Self‐Supervised Feature Fusion (SSF‐FT) method enhances low‐resource speech recognition by adaptively combining features from self‐supervised models trained with Contrastive, Predictive, and Reconstruction objectives. This attention‐weighted ensemble delivers robust performance, particularly in acoustically challenging conditions, extending current
Ussen Kimanuka +2 more
wiley +1 more source
The Phonetics and Phonology of Chuxnaban Mixe
Linguistic Discovery, 2011 This paper presents the first detailed description of the phonetic structures of the endangered Mexican indigenous language Chuxnab?n Mixe, including a survey of the main features of the consonant system and acoustic measurements of the characteristics ...
Carmen Jany
doaj +1 more source
Von Kempelen et al. : remarks on the history of articulatory-acoustic modelling [PDF]
, 2005 The contribution of von Kempelen’s “Mechanism of Speech” to the ‘phonetic sciences‘ will be analyzed with respect to his theoretical reasoning on speech and speech production on the one hand and on the other in connection with his practical insights ...
Pompino-Marschall, Bernd
core
On the Optimal Selection of Mel‐Frequency Cepstral Coefficients for Voice Deepfake Detection
Expert Systems, Volume 43, Issue 5, May 2026.ABSTRACT The continuous evolution of techniques for generating manipulated audio, known as voice deepfakes, and the widespread availability of tools that produce convincing forgeries have created an urgent need for reliable detection methods. This work considers the dimensionality of Mel‐Frequency Cepstral Coefficients (MFCCs) as a core design variable
Sergio A. Falcón‐López +3 more
wiley +1 more source
Characterizing intonation deficit in motor speech disorders : an autosegmental-metrical analysis of spontaneous speech in hypokinetic dysarthria, ataxic dysarthria and foreign accent syndrome [PDF]
, 2012 The autosegmental-metrical (AM) framework represents an established methodology for intonational analysis in unimpaired speaker populations but has found little application in describing intonation in motor speech disorders (MSDs).
Kuschmann, Anja, Lowit, Anja
core +1 more source
Rapid Mandarin Tone Learning in Passive and Active Listening: A Magnetoencephalography Study
European Journal of Neuroscience, Volume 63, Issue 7, April 2026.This study investigated how 4 days of passive and active listening to Mandarin tone changes in /a/ affected behavioral change detection and MEG responses in native Finnish‐speaking adults. Perceptual learning of foreign speech sounds was reflected in enhanced magnetic mismatch negativity and N2b as well as improved behavioral accuracy.
Kaijun Jiang +6 more
wiley +1 more source
CNN‐Based Accent Similarity Detection Using Masked Spectrogram Reconstruction
Engineering Reports, Volume 8, Issue 3, March 2026.Convolutional Neural Network Masked Spectrogram Reconstruction model to enhance accent recognition and similarity assessment in automatic speech recognition. Addressing challenges in recognizing non‐native English accents, the method utilizes randomly masked spectrogram inputs to extract accent‐specific features.
Amina Salifu +8 more
wiley +1 more source
An acoustic study of plain and palatalized sibilants in Ocotepec Mixe [PDF]
, 2009 In Ocotepec Mixe, the stem-initial sibilants /s tÉs ß/ undergo a palatalization process when the prefix /j/ is added. Descriptions of other Mixe languages report that this palatalization is realized either as addition of a glide (in the case of the ...
Avelino, Heriberto, Hamann, Silke
core