Your search
Results 20 resources
-
BAGLS-RT is an extension of the BAGLS dataset (DOI 10.5281/zenodo.3762320) intended for (re-)training glottis segmentation models.
-
BAGLS is a benchmark dataset intended to compare performance across automatic glottis segmentation methods.
-
The frequencies, magnitudes, and bandwidths of vocal tract resonances are all important in understanding and synthesizing speech. High precision acoustic impedance spectra of the vocal tracts of 10 subjects were measured from 10 Hz to 4.2 kHz by injecting a broadband acoustic signal through the lips. Between 300 Hz and 4 kHz the acoustic resonances R (impedance minima measured through the...
-
A zip archive of several series of DICOM files from two ex-vivo hyoid specimens: one adult and one child. Each specimen was scanned at different slice thicknesses, as described and used in Cotter et al., 2015.
-
A zip archive of several series of DICOM files from three ex-vivo mandible specimens: two adult and one child. Each specimen was scanned at different slice thicknesses, as described and used in Whyms et al., 2013.
-
This dataset contains simultaneous recordings of electroglottography (EGG recorded with Glottal Enterprises EG2-PCX2), unfiltered audio, and intraoral pressure (recorded with Glottal Enterprises PG-60) from 14 subjects. It is meant to facilitate the validation of physical models of glottal control during voicing, in which the glottal/source waveform for speech is controlled by a combination of...
-
Abstract A detailed understanding of how the acoustic patterns of speech sounds are generated by the complex 3D shapes of the vocal tract is a major goal in speech research. The Dresden Vocal Tract Dataset (DVTD) presented here contains geometric and (aero)acoustic data of the vocal tract of 22 German speech sounds (16 vowels, 5 fricatives, 1 lateral), each from one male and one...
-
Currently available data set consists of the DICOM-datafiles and corresponding sound samples for all the finnish vowels. Some derivatives obtained from the image and sound data are also provided, this includes the surface models for the vowels.
-
Abstract The use of real-time magnetic resonance imaging (rt-MRI) of speech is increasing in clinical practice and speech science research. Analysis of such images often requires segmentation of articulators and the vocal tract, and the community is turning to deep-learning-based methods to perform this segmentation. While there are publicly available rt-MRI datasets of speech,...
-
Abstract The study of articulatory gestures has a wide spectrum of applications, notably in speech production and recognition. Sets of phonemes, as well as their articulation, are language-specific; however, existing MRI databases mostly include English speakers. In our present work, we introduce a dataset acquired with MRI from 10 healthy native French speakers. A corpus...
-
Welcome to our interactive International Phonetic Association (IPA) chart website! Clicking on the IPA symbols on our charts will allow you to listen to their sounds and see vocal-organ movements imaged with ultrasound, MRI, or in animated form. To find out more about how our IPA charts were made, click on the buttons on the left-hand side of this page. The website contains two main...
-
This is a corpus of articulatory data of different forms (EMA, MRI, video, 3D scans of upper/lower jaw, audio etc.) acquired from one male British English speaker.
-
The USC Speech and Vocal Tract Morphology MRI Database consists of real-time magnetic resonance images of dynamic vocal tract shaping during read and spontaneous speech with concurrently recorded denoised audio, and 3D volumetric MRI of vocal tract shapes during vowels and continuant consonants sustained for 7 seconds, from 17 speakers.
-
USC-EMO-MRI is an emotional speech production database which includes real-time magnetic resonance imaging data with synchronized speech audio from five male and five female actors, each producing a passage and a set of sentences in multiple repetitions, while enacting four different target emotions (neutral, happy, angry, sad). The database includes emotion quality evaluation from at least...
Explore
Audio Data
Derived & Measured Data
- Formant Measurements (1)
- Vocal Tract (4)
Software, Processing & Utilities
Speech Production Data
-
Vocal Anatomy
- Hyoid (1)
- Larynx and Glottis (3)
- Mandible and Maxilla (3)
- Mechanical Properties (1)
- Models (2)
- Vocal Tract (11)
- Articulography (2)
- MRI (10)
- Ultrasound (1)
- Video (1)
Teaching Resources
- 3D Models (1)
- Articulation Data (2)
Tags
- adult (11)
- MRI (9)
- audio data (9)
- male (8)
- real-time MRI (rtMRI) (8)
- female (7)
- read speech (7)
- English (6)
- articulatory data (5)
- volumetric MRI (5)
- segmentation (4)
- teaching resource (3)
- vowels (3)
- speech production (3)
- vocal tract shape (3)
- mandible (3)
- video (3)
- DICOM (3)
- computed tomography (CT) (3)
- source-filter model (2)
- tube model (2)
- STL files (2)
- articulation (2)
- multimodal (2)
- International Phonetic Alphabet (IPA) (2)
- electromagnetic articulography (EMA) (2)
- child (2)
- benchmark (2)
- glottis (2)
- videoendoscopy (2)
- MATLAB (1)
- area function (1)
- numerical acoustic modelling (1)
- vocal fold model (1)
- 3D print (1)
- phonetics (1)
- American English (1)
- angry (1)
- emotional speech (1)
- happy (1)
- perceptually annotated (1)
- sad (1)
- consonants (1)
- British (1)
- dentition (1)
- maxilla (1)
- lip video (1)
- ultrasound tongue imaging (UTI) (1)
- French (1)
- transcribed (1)
- finite element method (FEM) (1)
- electroglottography (EGG) (1)
- intraoral pressure (1)
- validation (1)
- hyoid (1)
- antiresonance (1)
- vocal tract length (1)
- vocal tract resonance (1)
Resource type
- Dataset (13)
- Journal Article (3)
- Software (2)
- Web Page (2)