Sökning: "Speech properties"

Visar resultat 21 - 25 av 56 avhandlingar innehållade orden Speech properties.

1. 21. The Voice Source in Speech Communication - Production and Perception Experiments Involving Inverse Filtering and Synthesis

   Författare :Christer Gobl; KTH; []
   Nyckelord :Voice source dynamics; glottal source parameters; source-filter interaction; voice quality; phonation; perception; affect; emotion; mood; attitude; paralinguistic; inverse filtering; knowledge-based; formant synthesis; LF model; fundamental frequency;

   Sammanfattning : This thesis explores, through a number of production andperception studies, the nature of the voice source signal andhow it varies in spoken communication. Research is alsopresented that deals with the techniques and methodologies foranalysing and synthesising the voice source. LÄS MER

3. 22. Swedish children with moderate hearing loss : on the importance of monitoring auditory and early speech development the first three years

   Författare :Anna Persson; Karolinska Institutet; Karolinska Institutet; []
   Nyckelord :;

   Sammanfattning : The overall aim of this thesis was to investigate the auditory and early speech development in a group of children born with moderate hearing loss (HL) who were fitted with hearing aids (HAs) before the age of 6 months, and to compare their development to a group of children with normal hearing (NH). More specific aims were to examine the impact of auditory variables on the early speech development in the children with HL and to validate a questionnaire of auditory development in the children with NH. LÄS MER

4. 23. Adaptive Robot Presenters : Modelling Grounding in Multimodal Interaction

   Författare :Agnes Axelsson; Gabriel Skantze; Johan Boye; Elisabeth André; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Human-robot interaction; Dialogue; Presentation; Museum; Grounding; Multimodal; Feedback; Classification; Knowledge graphs; KG; KG-to-text; WebNLG; System; Learning; Large Language Model; LLM; människa-robot-interaktion; hri; dialog; presentation; museum; grundning; multimodal; multimodalitet; återmatning; klassifikation; kunskapsgraf; kg; kg-till-text; data-tilltext; webnlg; system; inlärning; lärande. stor språkmodell; llm; Speech and Music Communication; Tal- och musikkommunikation;

   Sammanfattning : This thesis addresses the topic of grounding in human-robot interaction, that is, the process by which the human and robot can ensure mutual understanding. To explore this topic, the scenario of a robot holding a presentation to a human audience is used, where the robot has to process multimodal feedback from the human in order to adapt the presentation to the human's level of understanding. LÄS MER

5. 24. Morphosyntactic Corpora and Tools for Persian

   Författare :Mojgan Seraji; Joakim Nivre; Carina Jahani; Jan Hajic; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Persian; language technology; corpus; treebank; preprocessing; segmentation; part-of-speech tagging; dependency parsing; Computational Linguistics; Datorlingvistik;

   Sammanfattning : This thesis presents open source resources in the form of annotated corpora and modules for automatic morphosyntactic processing and analysis of Persian texts. More specifically, the resources consist of an improved part-of-speech tagged corpus and a dependency treebank, as well as tools for text normalization, sentence segmentation, tokenization, part-of-speech tagging, and dependency parsing for Persian. LÄS MER

7. 25. Predicting Linguistic Structure with Incomplete and Cross-Lingual Supervision

   Författare :Oscar Täckström; Joakim Nivre; Jussi Karlgren; Ryan McDonald; Hal Daumé III; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; linguistic structure prediction; structured prediction; latent-variable model; semi-supervised learning; multilingual learning; cross-lingual learning; indirect supervision; partial supervision; ambiguous supervision; part-of-speech tagging; dependency parsing; named-entity recognition; sentiment analysis; Computational Linguistics; Datorlingvistik;

   Sammanfattning : Contemporary approaches to natural language processing are predominantly based on statistical machine learning from large amounts of text, which has been manually annotated with the linguistic structure of interest. However, such complete supervision is currently only available for the world's major languages, in a limited number of domains and for a limited range of tasks. LÄS MER