Salvato in:
Dettagli Bibliografici
Autori principali: Teleki, Maria, Janjur, Sai, Liu, Haoran, Grabner, Oliver, Verma, Ketan, Docog, Thomas, Dong, Xiangjue, Shi, Lingfeng, Wang, Cong, Birkelbach, Stephanie, Kim, Jason, Zhang, Yin, Caverlee, James
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.20319
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916967747682304
author Teleki, Maria
Janjur, Sai
Liu, Haoran
Grabner, Oliver
Verma, Ketan
Docog, Thomas
Dong, Xiangjue
Shi, Lingfeng
Wang, Cong
Birkelbach, Stephanie
Kim, Jason
Zhang, Yin
Caverlee, James
author_facet Teleki, Maria
Janjur, Sai
Liu, Haoran
Grabner, Oliver
Verma, Ketan
Docog, Thomas
Dong, Xiangjue
Shi, Lingfeng
Wang, Cong
Birkelbach, Stephanie
Kim, Jason
Zhang, Yin
Caverlee, James
contents Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall performance but cannot reveal why models succeed or fail. We introduce Z-Scores, a span-level linguistically-grounded evaluation metric that categorizes system behavior across distinct disfluency types (EDITED, INTJ, PRN). Our deterministic alignment module enables robust mapping between generated text and disfluent transcripts, allowing Z-Scores to expose systematic weaknesses that word-level metrics obscure. By providing category-specific diagnostics, Z-Scores enable researchers to identify model failure modes and design targeted interventions -- such as tailored prompts or data augmentation -- yielding measurable performance improvements. A case study with LLMs shows that Z-Scores uncover challenges with INTJ and PRN disfluencies hidden in aggregate F1, directly informing model refinement strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20319
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Z-Scores: A Metric for Linguistically Assessing Disfluency Removal
Teleki, Maria
Janjur, Sai
Liu, Haoran
Grabner, Oliver
Verma, Ketan
Docog, Thomas
Dong, Xiangjue
Shi, Lingfeng
Wang, Cong
Birkelbach, Stephanie
Kim, Jason
Zhang, Yin
Caverlee, James
Computation and Language
Artificial Intelligence
Audio and Speech Processing
Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall performance but cannot reveal why models succeed or fail. We introduce Z-Scores, a span-level linguistically-grounded evaluation metric that categorizes system behavior across distinct disfluency types (EDITED, INTJ, PRN). Our deterministic alignment module enables robust mapping between generated text and disfluent transcripts, allowing Z-Scores to expose systematic weaknesses that word-level metrics obscure. By providing category-specific diagnostics, Z-Scores enable researchers to identify model failure modes and design targeted interventions -- such as tailored prompts or data augmentation -- yielding measurable performance improvements. A case study with LLMs shows that Z-Scores uncover challenges with INTJ and PRN disfluencies hidden in aggregate F1, directly informing model refinement strategies.
title Z-Scores: A Metric for Linguistically Assessing Disfluency Removal
topic Computation and Language
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2509.20319