ZASPiL 40 = Speech production and perception : Experimental analyses and models
Refine
Year of publication
- 2005 (14)
Document Type
- Part of a Book (14)
Language
- English (14)
Has Fulltext
- yes (14)
Is part of the Bibliography
- no (14)
Keywords
- Artikulation (6)
- Artikulatorische Phonetik (5)
- Artikulator (4)
- Phonetik (3)
- Akustische Phonetik (2)
- Auditive Phonetik (2)
- Computerlinguistik (2)
- Experimentelle Phonetik (2)
- Kernspintomographie (2)
- Lautsprache (2)
In order to understand the functional morphology of the human voice producing system, we are in need of data on the vocal tract anatomy of other mammalian species. The larynges and vocal tracts of four species of Artiodactyla were investigated in combination with acoustic analyses of their respective calls. Different evolutionary specializations of laryngeal characters may lead to similar effects on sound production. In the investigated species, such specializations are: the elongation and mass increase of the vocal folds, the volume increase of the laryngeal vestibulum by an enlarged thyroid cartilage and the formation of laryngeal ventricles. Both the elongation of the vocal folds and the increase of the oscillating masses lower the fundamental frequency. The influence of an increased volume of the laryngeal vestibulum on sound production remains unclear. The anatomical and acoustic results are presented together with considerations about the habitats and the mating systems of the respective species.
Four speakers repeated 8 times 15 sentences containing 'pVp' syllables (V being /a/, /i/ and /u/). The 'pVp' syllables were located in final, penultimate and antepenultimate position relatively to the Intonational Phrase (IP) boundary. They were embedded in lexical words of 1-3 syllables and were either word-initial or word-final. Results show that the closer the vowel in word-final position is to the IP boundary, the longer the duration and the higher the fundamental frequency of the vowel; it is also characterised by larger lip opening gestures. The potential reduction or coarticulation of vowels in wordinitial position compared to their counterparts in word-final position is discussed.
The author presents MASSY, the MODULAR AUDIOVISUAL SPEECH SYNTHESIZER. The system combines two approaches of visual speech synthesis. Two control models are implemented: a (data based) di-viseme model and a (rule based) dominance model where both produce control commands in a parameterized articulation space. Analogously two visualization methods are implemented: an image based (video-realistic) face model and a 3D synthetic head. Both face models can be driven by both the data based and the rule based articulation model.
The high-level visual speech synthesis generates a sequence of control commands for the visible articulation. For every virtual articulator (articulation parameter) the 3D synthetic face model defines a set of displacement vectors for the vertices of the 3D objects of the head. The vertices of the 3D synthetic head then are moved by linear combinations of these displacement vectors to visualize articulation movements. For the image based video synthesis a single reference image is deformed to fit the facial properties derived from the control commands. Facial feature points and facial displacements have to be defined for the reference image. The algorithm can also use an image database with appropriately annotated facial properties. An example database was built automatically from video recordings. Both the 3D synthetic face and the image based face generate visual speech that is capable to increase the intelligibility of audible speech.
Other well known image based audiovisual speech synthesis systems like MIKETALK and VIDEO REWRITE concatenate pre-recorded single images or video sequences, respectively. Parametric talking heads like BALDI control a parametric face with a parametric articulation model. The presented system demonstrates the compatibility of parametric and data based visual speech synthesis approaches.
The goal of our current project is to build a system that can learn to imitate a version of a spoken utterance using an articulatory speech synthesiser. The approach is informed and inspired by knowledge of early infant speech development. Thus we expect our system to reproduce and exploit the utility of infant behaviours such as listening, vocal play, babbling and word imitation. We expect our system to develop a relationship between the sound-making capabilities of its vocal tract and the phonetic/phonological structure of imitated utterances. At the heart of our approach is the learning of an inverse model that relates acoustic and motor representations of speech. The acoustic to auditory mappings uses an auditory filter bank and a self-organizing phase of learning. The inverse model from auditory to vocal tract control parameters is estimated using a babbling phase, in which the vocal tract is essentially driven in a random manner, much like the babbling phase of speech acquisition in infants. The complete system can be used to imitate simple utterances through a direct mapping from sound to control parameters. Our initial results show that this procedure works well for sounds generated by its own voice. Further work is needed to build a phonological control level and achieve better performance with real speech.