A5090223651- Phonetics and Phonology Research
- Research in Social Sciences
- Natural Language Processing Techniques
- Speech Recognition and Synthesis
- Linguistic Variation and Morphology
- Speech and dialogue systems
- Neuroscience and Music Perception
- Hearing Loss and Rehabilitation
- Subtitles and Audiovisual Media
- Music Technology and Sound Studies
- Digital Communication and Language
- Topic Modeling
- Text Readability and Simplification
- Interpreting and Communication in Healthcare
- linguistics and terminology studies
- European and International Law Studies
- Transportation Systems and Safety
- Environmental and Social Impact Assessments
- Speech and Audio Processing
- Language, Linguistics, Cultural Analysis
- Gender Studies in Language
- Swearing, Euphemism, Multilingualism
- Digital and Cyber Forensics
- Authorship Attribution and Profiling
- Business Process Modeling and Analysis
University of Helsinki
1997-2024
Aalto University
2022
TeliaSonera (Finland)
2022
University of Turku
2022
University of Jyväskylä
2008
Tampere University
2008
Magnetic brain responses to speech sounds were measured in 10 healthy neonates. The stimulation consisted of a frequent vowel sound [a:] with steady pitch contour, which was occasionally replaced by the [i:] pitch, or rising manifesting change intonation. magnetic mismatch-negativity response (MMNm) obtained and successfully modelled quality all infants intonation 6 infants. present results indicate that auditory-cortex speech-sound discrimination may well be studied recordings as early newborn
The Donate Speech campaign has so far succeeded in gathering approximately 3600 h of ordinary, colloquial Finnish speech into the
Our aim in this paper is to explore ways of modeling the distribution pause durations conversation using oscillator models (Wilson, Wilson 2006), and consider how these might be integrated into our Coupled Oscillator Model speech timing (COM (O'Dell, Lennes, Werner, Nieminen 2007; O'Dell, 2008;O'Dell, 2009)).
In this study, the temporal aspects of speech are compared in read-aloud Finnish produced by six native and 16 non-native speakers. It is shown that articulation rates as well pause durations different for Moreover, differences exist between groups speakers representing four languages. Surprisingly, tend to make longer pauses than non-natives. The results relevant when developing methods assessing fluency or strength foreign accent.
This study continues our previous investigation into the rhythms contributing to temporal structure of speech.The relative significance different hierarchical levels rhythm was evaluated using Bayesian inference on a linear regression model based coupled oscillators.Results strengthen conclusions that stress, mora and possibly foot timing are all simultaneously present as rhythmic factors in Finnish conversational speech.
In spontaneous speech, occurrences of the same word form vary phonetically. Words that do not receive sentence accent tend to be less clearly articulated and shorter in duration comparison prominent words. If such an unaccented is isolated from continuous it may even identifiable by listeners, but as part speech stream, usually easily identified helps listener perceive organize spoken message a whole. Thus, variability words random must follow certain patterns determined context. this study,...
We discuss the archiving procedure of a corpus comprising posts submitted to Torilauta, Finnish dark web marketplace website. The site was active from 2017 2021 and during this time one most prominent online illegal narcotics markets in Finland. A reduced version corpus, Dark Web Marketplace Corpus (FINDarC), has been archived Language Bank In current work, we focus on protective measures for storing data how researchers can apply access rights under CLARIN RES licence.