Acoustic Variation in Speech: Contrasting Initial and Later Stages of Conversations Showing Opinion Convergence and Divergence
Bibliographic record
Abstract
Speech accommodation is influenced by various factors, such as interlocutor traits, social identity, context, and opinion [Pardo, 2022 JPhon95]. Although the effects of many of these factors have been extensively researched, the relationship between opinion convergence or divergence and speaker traits is a relatively new area of interest [Ma et al., 2023, HISPCSL]. Another important factor affecting speech is the timepoint within a conversation, as individuals may modify their speech patterns as the conversation progresses. This study aimed to investigate whether the stage of a conversation (initial vs. later) influences the way individuals express opinion convergence or divergence in relation to their interlocutors. Using Praat, DARLA, and statistical methods in R software, we analyzed speech data from an Ellen Fisher Podcast YouTube debate on "Plant vs. Animal Regenerative Farming." Audio clips from the first and last 10 minutes of the debate were transcribed manually into words, automatically converted into phonemes using DARLA, and then manually verified. Each word was further coded for the speaker, interlocutor, whether they expressed convergence or divergence, and the strength of their convergence or divergence on a numerical scale. Preliminary findings revealed that speakers tended to raise their fundamental frequency (F0) when expressing divergence in opinion during deeper stages of the conversation, suggesting a relationship between speech patterns and opinion divergence in different conversation stages. However, we did not observe any significant effect of conversation stage on opinion convergence. Furthermore, no differences were found in terms of vowel quality, as measured by F1 and F2. These preliminary results shed light on the complex interplay between conversation stage and the expression of opinion divergence in speech. Further analysis and exploration of these findings will provide a deeper understanding of the dynamics of speech accommodation in relation to opinion expression within conversations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".