Papers by Ioana Vasilescu

5 papers
Using Speech Technology to Test Theories of Phonetic and Phonological Typology (2024.lrec-main)

Copied to clipboard

Challenge: acoustic studies show that obstruents in European Portuguese have different voicing profiles than their Romance relatives.
Approach: They propose to use speech technology to test phonetic typology in European Portuguese . they use acoustic phone models to force align different phone models for obstruents .
Outcome: The proposed method supports previous accounts that European Portuguese is diverging from the traditional voicing system known for Romance languages towards a hybrid system where stops and fricatives are specified for different voicing features.
Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation (2022.lrec-1)

Copied to clipboard

Challenge: Speech characteristics vary from speaker to speaker due to many factors, including communication context, provenance, age, and social background.
Approach: They propose a method that uses a knowledge base to provide speaker-specific information.
Outcome: The proposed method can be used to enrich existing corpora with speaker-specific information and to correlate with diastratic features.
Linguistic Nudges and Verbal Interaction with Robots, Smart-Speakers, and Humans (2024.lrec-main)

Copied to clipboard

Challenge: nudges are a choice architecture that alters people's behavior without forbidding any options or significantly changing their economic incentives.
Approach: They describe a data collection methodology and emotion annotation of dyadic interactions between a human, a Pepper robot, . a Google Home smart-speaker, and other humans.
Outcome: The collected 16-hour audio recordings show that humans change their opinions on more questions with a human than with nudges, even against mainstream ideas.
Corpus Design for Studying Linguistic Nudges in Human-Computer Spoken Interactions (2022.lrec-1)

Copied to clipboard

Challenge: linguistic nudges can influence people to the same degree as a human agent, according to Thaler and Sunstein (2008).
Approach: They propose to use a corpus design method to compare influence between linguistic nudges with positive or negative influences and three conversational agents: robot, smart speaker, and human.
Outcome: The results show that linguistic nudges can influence participants to the same degree as human agents.
Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages (2022.lrec-1)

Copied to clipboard

Challenge: voicing alternation phenomena of stops are a common problem in connected speech . phoneticians and phonologists are interested in analyzing phonetic variation .
Approach: They use forced alignment with pronunciation variants and machine learning techniques to examine voicing alternations of stops in Romance languages.
Outcome: The proposed method enables linguists to use large corpora and speech recognition systems . the results show that voicing alternations occur in all Romance languages .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations