1 |
How are visemes and graphemes integrated with speech sounds during spoken word recognition? ERP evidence for supra-additive responses during audiovisual compared to auditory speech processing
|
|
|
|
In: ISSN: 0093-934X ; EISSN: 1090-2155 ; Brain and Language ; https://hal.archives-ouvertes.fr/hal-03472191 ; Brain and Language, Elsevier, 2022, 225, ⟨10.1016/j.bandl.2021.105058⟩ (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Multistream neural architectures for cued-speech recognition using a pre-trained visual feature extractor and constrained CTC decoding
|
|
|
|
In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing ; https://hal.archives-ouvertes.fr/hal-03578503 ; ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore (2022)
|
|
BASE
|
|
Show details
|
|
3 |
Investigating the locus of transposed-phoneme effects using cross-modal priming
|
|
|
|
In: ISSN: 0001-6918 ; EISSN: 1873-6297 ; Acta Psychologica ; https://hal.archives-ouvertes.fr/hal-03619856 ; Acta Psychologica, Elsevier, 2022, 226, pp.103578. ⟨10.1016/j.actpsy.2022.103578⟩ (2022)
|
|
BASE
|
|
Show details
|
|
4 |
Potential of automatic speech processing technologies for early detection of oral language disorders: a meta-analytic review ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
A comparative study of several parameterizations for speaker recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Speaker verification in mismatch training and testing conditions ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Estimating Vocal Tract Resonances of Synthesized High-Pitched Vowels Using CNN ...
|
|
|
|
Abstract:
Beim Sprechen oder Singen wird ein vom Kehlkopf kommender Schall durch den Vokaltrakt gefiltert. Formanten, die Maxima des resultierenden Spektrums, bestimmen den Vokal und die Stimmfarbe. Bei Sprachfrequenzen liegen die Obertöne der Schallquelle dicht beieinander, so dass die Maxima des Ausgangsspektrums weitgehend mit den Resonanzfrequenzen des Vokaltraktfilters übereinstimmen. Bei höheren Grundfrequenzen, wie bei Gesang oder Kindersprache, werden die Maxima des Ausgangsspektrums eher durch die Lage der Obertöne als durch die Resonanzfrequenzen bestimmt. Die üblichen Verfahren zur Formantschätzung, LPC und Cepstrum, basieren auf der spektralen Hüllkurve. Sie funktionieren gut bei Sprachfrequenzen, aber bei höheren Grundfrequenzen bestimmen sie die Obertöne statt die Resonanzfrequenzen. Informationen über die Lage der Resonanzen sind jedoch immer noch im Klang vorhanden, z. B. in der Behauchung und im Vibrato. Eine Methode, die in der Lage ist, diese Informationen bei hohen Frequenzen zu erkennen, würde das ... : In speaking or singing, a source sound coming from the larynx is filtered by the vocal tract. Formants, the maxima of the resulting spectrum, determine the vowel and the timbre of the voice. At speech frequencies, between 100 Hz - 400 Hz, the harmonics of the source sound are spaced densely, so the peaks of the output spectrum largely correspond to the resonance frequencies of the vocal tract filter. At higher fundamental frequencies, like in singing or child speech, the peaks of the output spectrum are determined more by the location of the harmonics than of the filter resonance frequencies. Traditional formant estimation methods, LPC and cepstrum, only use information from the spectral envelope. They perform well at speech frequencies, but at higher fundamental frequencies, they are not able to find the resonance frequencies of the vocal tract and determine the harmonics instead. Information about the location of the resonances is however still present in the sound, e.g. in breathiness and vibrato. A ...
|
|
Keyword:
Formant estimation; High pitch; Neural network; Speech processing; Vocal tract resonance
|
|
URL: https://dx.doi.org/10.34726/hss.2022.89401 https://repositum.tuwien.at/handle/20.500.12708/19264
|
|
BASE
|
|
Hide details
|
|
8 |
A New Amharic Speech Emotion Dataset and Classification Benchmark ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Automatic Dialect Density Estimation for African American English ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Data From: A Protracted Developmental Trajectory for English-Learning Children’s Detection of Consonant Mispronunciations in Newly Learned Words
|
|
|
|
In: Speech and Hearing Sciences Faculty Datasets (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Learning and controlling the source-filter representation of speech with a variational autoencoder ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Correcting Misproducted Speech using Spectrogram Inpainting ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Repeat after me: Self-supervised learning of acoustic-to-articulatory mapping by vocal imitation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Can Social Robots Effectively Elicit Curiosity in STEM Topics from K-1 Students During Oral Assessments? ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Expression-preserving face frontalization improves visually assisted speech processing ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|