Alexandra Markó
YOU?
Author Swipe
View article: Optimizing the Ultrasound Tongue Image Representation for Residual Network-Based Articulatory-to-Acoustic Mapping
Optimizing the Ultrasound Tongue Image Representation for Residual Network-Based Articulatory-to-Acoustic Mapping Open
Within speech processing, articulatory-to-acoustic mapping (AAM) methods can apply ultrasound tongue imaging (UTI) as an input. (Micro)convex transducers are mostly used, which provide a wedge-shape visual image. However, this process is o…
View article: Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces
Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces Open
Articulatory-to-acoustic mapping seeks to reconstruct speech from a recording of the articulatory movements, for example, an ultrasound video. Just like speech signals, these recordings represent not only the linguistic content, but are al…
View article: Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input Open
Articulatory information has been shown to be effective in improving the performance of HMM-based and DNN-based text-to-speech synthesis. Speech synthesis research focuses traditionally on text-to-speech conversion, when the input is text …
View article: Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging Open
For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation…
View article: The realization of voicing opposition in alveolar fricatives in Hungarian
The realization of voicing opposition in alveolar fricatives in Hungarian Open
The simultaneous articulation of the turbulent noise of fricatives and vocal fold vibration poses difficulties due to their conflicting pressure requirements. Previous studies found advanced tongue root and narrower obstacle in voiced fricati…
View article: Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces
Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces Open
Articulatory-to-acoustic mapping seeks to reconstruct speech from a recording of the articulatory movements, for example, an ultrasound video.Just like speech signals, these recordings represent not only the linguistic content, but are als…
View article: Subsegmental differences between accented and unaccented vowels in Hungarian
Subsegmental differences between accented and unaccented vowels in Hungarian Open
In the present study we searched for an answer to the question if in Hungarian, similarly to the so far investigated Germanic languages, accent results in sonority expansion and/or localized hyperarticulation. The analysis was performed by…
View article: Transducer Misalignment in Ultrasound Tongue Imaging
Transducer Misalignment in Ultrasound Tongue Imaging Open
A long-standing problem for ultrasound tongue imaging is the transducer misalignment during longer data recording sessions. In this paper, we present an initial idea for analyzing such misalignment. The method employs Mean Square Error (MS…
View article: Acoustic and articulatory vowel variation as quality shift and increased variance in anticipatory and carryover vowel-to-vowel coarticulation
Acoustic and articulatory vowel variation as quality shift and increased variance in anticipatory and carryover vowel-to-vowel coarticulation Open
In this paper we studied if we find increased coarticulatory
\nresistance and aggression in V-to-V coarticulation in pitchaccented
\nsyllables, and we also tested if anticipatory effects are
\nexceeded by carryover effects in these context…
View article: Tongue root position in VC sequences with regard to the phonetic realization of obstruent voicing: A preliminary study on Hungarian
Tongue root position in VC sequences with regard to the phonetic realization of obstruent voicing: A preliminary study on Hungarian Open
In this paper we studied the tongue root position in VCsequences with regard to the phonological voicing of the consonant and its phonetic realization. /iz/ and /is/ sequences were recorded embedded into carrier sentences in 12 speakers’ p…
View article: Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging Open
For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2.In this paper, we experimented with transfer learning and adaptation …
View article: Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input Open
Articulatory information has been shown to be effective in improving the performance of HMM-based and DNN-based textto-speech synthesis.Speech synthesis research focuses traditionally on text-to-speech conversion, when the input is text or…
View article: Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis
Ultrasound-Based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis Open
For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality. Th…
View article: Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech\n Synthesis
Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech\n Synthesis Open
For articulatory-to-acoustic mapping using deep neural networks, typically\nspectral and excitation parameters of vocoders have been used as the training\ntargets. However, vocoding often results in buzzy and muffled final speech\nquality.…
View article: Articulatory studies in Hungary – past, present and future
Articulatory studies in Hungary – past, present and future Open
Articulatory studies performed in Hungary date back to the sixties, when different methods were applied for the description of the segment inventory of Hungarian and various other languages (e.g. Russian, German, English, Polish). Palato- …
View article: Glottal marking in sentence reading: Comparison of adolescents' and adults' speech production
Glottal marking in sentence reading: Comparison of adolescents' and adults' speech production Open
Glottal marking is well described for adult speakers; however, children’s speech has been less documented yet. The present study analysed the appearance of glottal marking in 16 adolescent (16- and 17-year-old) and 16 adult (20- to 45-year…
View article: Intervocalic voicing of Hungarian /h/
Intervocalic voicing of Hungarian /h/ Open
In this study, we investigated whether the amount of voicing, and the sound quality (expressed in HNR) of /h/ in syllable onset are affected by intervocalic context (vs. post-pausal context), by backness and openness of the flanking vowels…
View article: Approaches to Hungarian
Approaches to Hungarian Open
This volume contains selected papers from the 13th International Conference on the Structure of Hungarian (Budapest, 2017).The contributions address current issues in Hungarian linguistics, including comparisons with other languages (e.g.,…
View article: Applying DNN Adaptation to Reduce the Session Dependency of Ultrasound Tongue Imaging-based Silent Speech Interfaces
Applying DNN Adaptation to Reduce the Session Dependency of Ultrasound Tongue Imaging-based Silent Speech Interfaces Open
Silent Speech Interfaces (SSI) perform articulatory-to-acoustic mapping to convert articulatory movement into synthesized speech. Its main goal is to aid the speech handicapped, or to be used as a part of a communication system operating i…
View article: Articulatory Analysis of Transparent Vowel /iː/ in Harmonic and Antiharmonic Hungarian Stems: Is There a Difference?
Articulatory Analysis of Transparent Vowel /iː/ in Harmonic and Antiharmonic Hungarian Stems: Is There a Difference? Open
The aim of our study is to analyse the articulatory characteristics of /iː/ occurring in Hungarian monosyllabic harmonic and antiharmonic stems.In their frequently cited work, based on 3 speakers' data, Beňuš and Gafos (2007) [1] claimed t…
View article: Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder
Ultrasound-Based Silent Speech Interface Built on a Continuous Vocoder Open
Recently it was shown that within the Silent Speech Interface (SSI) field, the prediction of F0 is possible from Ultrasound Tongue Images (UTI) as the articulatory input, using Deep Neural Networks for articulatory-to-acoustic mapping. Mor…
View article: Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces
Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces Open
When using ultrasound video as input, Deep Neural Network-based Silent Speech Interfaces usually rely on the whole image to estimate the spectral parameters required for the speech synthesis step. Although this approach is quite straightfo…
View article: Megnyilatkozáskezdő magánhangzók glottális jelöltsége a szintaktikai pozíció és a magánhangzó-minőség függvényében
Megnyilatkozáskezdő magánhangzók glottális jelöltsége a szintaktikai pozíció és a magánhangzó-minőség függvényében Open
Glottal marking of utterance-initial vowels as a function of the syntactic position and the vowel quality In the present study, the glottal marking of utterance-initially appearing vowels was analysed with respect to the syntactic position…
View article: Gemináták artikulációs szerveződése a magyarban
Gemináták artikulációs szerveződése a magyarban Open
Articulatory organization of geminates in Hungarian It is traditionally assumed that geminates undergo degemination when being flanked by another consonant in Hungarian. As in Hungarian duration is considered to be the main acoustic cue to…
View article: Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent\n Speech Interfaces
Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent\n Speech Interfaces Open
When using ultrasound video as input, Deep Neural Network-based Silent Speech\nInterfaces usually rely on the whole image to estimate the spectral parameters\nrequired for the speech synthesis step. Although this approach is quite\nstraigh…
View article: A magyar /h/ zöngésedése magánhangzók között
A magyar /h/ zöngésedése magánhangzók között Open
In our research we aim to examine this allophonic alternation of the laryngeal fricative from a phonetic point of view, in an attempt to shed more light on the phonetic and phonological factors that may facilitate or restrain the occurrenc…
View article: Mondathangsúlyos és hangsúlytalan helyzetű magánhangzók néhány artikulációs és akusztikai jellemzője a magyarban
Mondathangsúlyos és hangsúlytalan helyzetű magánhangzók néhány artikulációs és akusztikai jellemzője a magyarban Open
In the present study three members of the Hungarian vowel inventory (/i/, /u/, /ɒ/) were analysed as a function of prominence, with respect to gender and vowel quality. The theoretically most prominent (stressed and accented) and non-promi…
View article: Speech Rate and Vowel Quality Effects on Vowel-related Word-initial Irregular Phonation in Hungarian
Speech Rate and Vowel Quality Effects on Vowel-related Word-initial Irregular Phonation in Hungarian Open
We examined utterance-initial irregular phonation as a function of vowel quality (vowel height and backness), and speech rate in Hungarian. In the analysis we distinguished two types of irregular phonation: glottalization and glottal stop.…