Eleanor Chodroff

EDBT 2026 Demo / reviewers in the wild / expert

dblp:184/8803 · DBLP profile ↗

← Back

18ranked-venue papers

4as first author

13since 2021 · last 2025

0000-0003-4549-5919ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 18 · 4 first-author · 13 since 2021Graphics, computer vision, multimedia, augmented reality and games · 8 · 2 first-author · 6 since 2021

Year	Publication	Venue	Position
2025	ZIPA: A family of efficient models for multilingual phone recognition abstract We present ZIPA, a family of efficient speech models that advances the state-of-the-art performance of crosslinguistic phone recognition.We first curated IPAPACK++, a large-scale multilingual speech corpus with 17,132 hours of normalized phone transcriptions and a novel evaluation set capturing unseen languages and sociophonetic variation.With the large-scale training data, ZIPA, including transducer (ZIPA-T) and CTC-based (ZIPA-CR) variants, leverage the efficient Zipformer backbones and outperform existing phone recognition systems with much fewer parameters.Further scaling via noisy student training on 11,000 hours of pseudo-labeled multilingual data yields further improvement.While ZIPA achieves strong performance on benchmarks, error analysis reveals persistent limitations in modeling sociophonetic diversity, underscoring challenges for future research. Farhan Samir, Eleanor Chodroff, David R. Mortensen	ACL (1)	3
2025	Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis Aref Farhadipour, Annie Baker, Bogdan Pricop, Eleanor Chodroff	INTERSPEECH	6
2024	What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages abstract Nadav Borenstein, Anej Svete, Robin Chan, Josef Valvoda, Franz Nowak, Isabelle Augenstein, Eleanor Chodroff, Ryan Cotterell. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024. Nadav Borenstein, Anej Svete, Robin Shing Moon Chan, Josef Valvoda, Franz Nowak, Isabelle Augenstein, Eleanor Chodroff, Ryan Cotterell	ACL (1)	7
2024	Phonetic Segmentation of the UCLA Phonetics Lab Archive abstract Research in speech technologies and comparative linguistics depends on access to diverse and accessible speech data. The UCLA Phonetics Lab Archive is one of the earliest multilingual speech corpora, with long-form audio recordings and phonetic transcriptions for 314 languages (Ladefoged et al., 2009). Recently, 95 of these languages were time-aligned with word-level phonetic transcriptions (Li et al., 2021). Here we present VoxAngeles, a corpus of audited phonetic transcriptions and phone-level alignments of the UCLA Phonetics Lab Archive, which uses the 95-language CMU re-release as our starting point. VoxAngeles also includes word- and phone-level segmentations from the original UCLA corpus, as well as phonetic measurements of word and phone durations, vowel formants, and vowel f0. This corpus enhances the usability of the original data, particularly for quantitative phonetic typology, as demonstrated through a case study of vowel intrinsic f0. We also discuss the utility of the VoxAngeles corpus for general research and pedagogy in crosslinguistic phonetics, as well as for low-resource and multilingual speech technologies. VoxAngeles is free to download and use under a CC-BY-NC 4.0 license. Eleanor Chodroff, Blaz Pazon, Annie Baker, Steven Moran	LREC/COLING	1
2024	On the Role of Context in Reading Time Prediction abstract We present a new perspective on how readers integrate context during real-time language comprehension.Our proposals build on surprisal theory, which posits that the processing effort of a linguistic unit (e.g., a word) is an affine function of its in-context information content.We first observe that surprisal is only one out of many potential ways that a contextual predictor can be derived from a language model.Another one is the pointwise mutual information (PMI) between a unit and its context, which turns out to yield the same predictive power as surprisal when controlling for unigram frequency.Moreover, both PMI and surprisal are correlated with frequency.This means that neither PMI nor surprisal contains information about context alone.In response to this, we propose a technique where we project surprisal onto the orthogonal complement of frequency, yielding a new contextual predictor that is uncorrelated with frequency.Our experiments show that the proportion of variance in reading times explained by context is a lot smaller when context is represented by the orthogonalized predictor.From an interpretability standpoint, this indicates that previous studies may have overstated the role that context has in predicting reading times.https://github.com/rycolab/ context-reading-time Andreas Opedal, Eleanor Chodroff, Ryan Cotterell, Ethan Wilcox	EMNLP	2
2024	The Use of Phone Categories and Cross-Language Modeling for Phone Alignment of Panãra Emily P. Ahn, Eleanor Chodroff, Myriam Lapierre, Gina-Anne Levow	INTERSPEECH	2
2024	Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment Rotem Rousso, Eyal Cohen, Joseph Keshet, Eleanor Chodroff	INTERSPEECH	4
2023	An Outlier Analysis of Vowel Formants from a Corpus Phonetics Pipeline Emily P. Ahn, Gina-Anne Levow, Richard A. Wright, Eleanor Chodroff	INTERSPEECH	4
2022	Fundamental Frequency Variability over Time in Telephone Interactions abstract Speech signals contain substantial fundamental frequency (f0) variability. Even within a single utterance, speakers modify f0 to create different intonational patterns. Previous studies have identified markers of increased f0 variability, such as the introduction of a new topic or greetings, but these are limited in the scope of their analyses. In the present study, we investigate f0 variability over the course of a telephone conversation, with a focus on the initial and medial utterances within the exchange. We examined f0 standard deviation of each utterance in over 2000 telephone conversations from 509 American English speakers from the Switchboard corpus. Findings showed that on average, speakers exhibit more f0 variability in the opening compared to mid-conversation utterances. Further, findings suggest that the inclusion of a greeting word in an initial turn, e.g., "hello” or "hi”, corresponds to an increase in f0 standard deviation. These results suggest that speakers employed more variable f0 in the initial few turns of a telephone conversation. The interpretation of this finding is multifaceted and may be linked to several communicative goals, including the placement of identity markers in conversation or the attraction of attention, or the role of openings as boundary markers. Leah Bradshaw, Eleanor Chodroff, Lena A. Jäger, Volker Dellwo	INTERSPEECH	2
2022	DeepFry: Identifying Vocal Fry Using Deep Neural Networks abstract Vocal fry or creaky voice refers to a voice quality characterized by irregular glottal opening and low pitch. It occurs in diverse languages and is prevalent in American English, where it is used not only to mark phrase finality, but also sociolinguistic factors and affect. Due to its irregular periodicity, creaky voice challenges automatic speech processing and recognition systems, particularly for languages where creak is frequently used. This paper proposes a deep learning model to detect creaky voice in fluent speech. The model is composed of an encoder and a classifier trained together. The encoder takes the raw waveform and learns a representation using a convolutional neural network. The classifier is implemented as a multi-headed fully-connected network trained to detect creaky voice, voicing, and pitch, where the last two are used to refine creak prediction. The model is trained and tested on speech of American English speakers, annotated for creak by trained phoneticians. We evaluated the performance of our system using two encoders: one is tailored for the task, and the other is based on a state-of-the-art unsupervised representation. Results suggest our best-performing system has improved recall and F1 scores compared to previous methods on unseen data. Bronya Roni Chernyak, Talia Ben Simon, Yael Segal-Feldman, Jeremy Steffman, Eleanor Chodroff, Jennifer Cole 0001, Joseph Keshet	INTERSPEECH	5
2022	VoxCommunis: A Corpus for Cross-linguistic Phonetic Analysis abstract Cross-linguistic phonetic analysis has long been limited by data scarcity and insufficient computational resources. In the past few years, the availability of large-scale cross-linguistic spoken corpora has increased dramatically, but the data still require considerable computational power and processing for downstream phonetic analysis. To facilitate large-scale cross-linguistic phonetic research in the field, we release the VoxCommunis Corpus, which contains acoustic models, pronunciation lexicons, and word- and phone-level alignments, derived from the publicly available Mozilla Common Voice Corpus. The current release includes data from 36 languages. The corpus also contains acoustic-phonetic measurements, which currently consist of formant frequencies (F1–F4) from all vowel quartiles. Major advantages of this corpus for phonetic analysis include the number of available languages, the large amount of speech per language, as well as the fact that most language datasets have dozens to hundreds of contributing speakers. We demonstrate the utility of this corpus for downstream phonetic research in a descriptive analysis of language-specific vowel systems, as well as an analysis of “uniformity” in vowel realization across languages. The VoxCommunis Corpus is free to download and use under a CC0 license. Emily P. Ahn, Eleanor Chodroff	LREC	2
2022	UniMorph 4.0: Universal Morphology abstract The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation, and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements on several fronts that were made in the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 66 new languages, including 24 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g., missing gender and macrons information. We have amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet. Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieras, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina J. Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Lane 0002, Mohit Raj, Matt Coler, Jaime Rafael Montoya Samame, Delio Siticonatzi Camaiteri, Esaú Zumaeta Rojas, Didier López Francis, Arturo Oncevay, Juan López Bautista, Gema Celeste Silva Villegas, Lucas Torroba Hennigen, Adam Ek, David Guriel, Peter Dirix, Jean-Philippe Bernardy, Andrey Scherbakov, Aziyana Bayyr-ool, Antonios Anastasopoulos, Roberto Zariquiey, Karina Sheifer, Sofya Ganieva, Hilaria Cruz, Ritván Karahóga, Stella Markantonatou, George Pavlidis, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Candy Angulo, Jatayu Baxi, Andrew Krizhanovsky, Natalia Krizhanovskaya, Elizabeth Salesky, Clara Vania, Sardana Ivanova, Jennifer C. White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo Maria Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar 0002, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Tucker Prud'hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova	LREC	88
2022	The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects abstract In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin. The corpus currently contains 357 recordings (about 9.6 hours) of monosyllabic words, disyllabic words, short sentences, a short passage and a poem, each produced in Standard Mandarin and in one of six regional Mandarin dialects: Beijing, Chengdu, Jinan, Taiyuan, Wuhan, and Xi’an Mandarin from 36 speakers. The corpus was collected remotely using participant-controlled smartphone recording apps. Word- and phone-level alignments were generated using Praat and the Montreal Forced Aligner. The pilot study of dialect-specific tone systems showed that with practicable design and decent recording quality, remotely collected speech data can be suitable for analysis of relative patterns in acoustic-phonetic realization. The corpus is available on OSF (https://osf.io/fgv4w/) for non-commercial use under a CC BY-NC 3.0 license. Eleanor Chodroff	LREC	2
2020	A Corpus for Large-Scale Phonetic Typology abstract A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. Access to such data can greatly facilitate investigation of phonetic typology at a large scale and across many languages. However, it is non-trivial and computationally intensive to obtain such alignments for hundreds of languages, many of which have few to no resources presently available. We describe the methodology to create our corpus, discuss caveats with current methods and their impact on the utility of this data, and illustrate possible research directions through a series of case studies on the 48 highest-quality readings. Our corpus and scripts are publicly available for non-commercial use at https://voxclamantisproject.github.io. Elizabeth Salesky, Eleanor Chodroff, Tiago Pimentel, Matthew Wiesner, Ryan Cotterell, Alan W. Black, Jason Eisner	ACL	2
2020	Predicting Declension Class from Form and Meaning abstract The noun lexica of many natural languages are divided into several declension classes with characteristic morphological properties.Class membership is far from deterministic, but the phonological form of a noun and its meaning can often provide imperfect clues.Here, we investigate the strength of those clues.More specifically, we operationalize "strength" as measuring how much information, in bits, we can glean about declension class from knowing the form and meaning of nouns.We know that form and meaning are often also indicative of grammatical gender-which, as we quantitatively verify, can itself share information with declension class-so we also control for gender.We find for two Indo-European languages (Czech and German) that form and meaning share a significant amount of information with class (and contribute additional information beyond gender).The three-way interaction between class, form, and meaning (given gender) is also significant.Our study is important for two reasons: First, we introduce a new method that provides additional quantitative support for a classic linguistic finding that form and meaning are relevant for the classification of nouns into declensions.Second, we show not only that individual declension classes vary in the strength of their clues within a language, but also that the variations between classes vary across languages.The code is publicly available at https://github.com/ rycolab/declension-mi. Adina Williams, Tiago Pimentel, Hagen Blix, Arya McCarthy, Eleanor Chodroff, Ryan Cotterell	ACL	5
2019	Testing the Distinctiveness of Intonational Tunes: Evidence from Imitative Productions in American English abstract Understanding the structure of intonational variation is a longstanding issue in prosodic research.A given utterance can be realized with countless intonational contours, and while variation in prosodic meaning is also large, listeners nevertheless converge on relatively consistent form-function mappings.While this suggests the existence of abstract intonational representations, it has been unclear how exactly these are defined.The present study examines the validity of a well-defined set of phonological representations for the generation of intonation in the nuclear region of an intonational phrase in American English: namely, the combination of binary pitch accents (H/L), phrase accents (H-/L-), and boundary tones (H%/L%) proposed in Pierrehumbert (1980).In an exploratory study, we examined whether speakers maintained the eight-way distinction among intonational contours posited to exist in this representational system.We created eight synthesized contours according to Pierrehumbert (1980) and examined whether listeners generalized these contours to novel productions.Speakers largely distinguished rising from nonrising contours in production, but few other distinctions were maintained.While this does not rule out the existence of additional contours in production, these findings do suggest that the representation of rising and non-rising contours may be privileged and more readily accessible in the intonational grammar. Eleanor Chodroff, Jennifer Cole 0001	INTERSPEECH	1
2018	Information Structure, Affect and Prenuclear Prominence in American English abstract The influence of information structure (IS: givenness, accessibility, newness and focus) on pitch accent assignment and acoustic prominence measures of prenuclear words was investigated for American English speech elicited through read production of mini-stories. Results showed a consistent pattern of accenting the initial content word in the sentence, supporting an analysis of prenuclear accent as structural, or ‘rhythmic’. While no association was observed between IS and accent type (e.g., H, L, L+H, L+H), the acoustic-phonetic realization of prominence was modulated by information structure. In particular, words that carry contrastive focus generally showed more extreme f0 excursions relative to the average. In addition, there was a strong influence of speaking style or ‘affect’ on both pitch accent type and the acoustic-phonetic realization of prominence. Speakers were more likely to produce L+H* accents in a lively than a neutral speaking style. Differences in affect were also strongly reflected in f0 excursion, duration, and amplitude within the target word. Overall, this study indicates both linguistic (information structure) and paralinguistic (affect) influences on the phonetic implementation of prenuclear prominence, with varying influence of these two factors on the phonological assignment of prenuclear pitch accents. Eleanor Chodroff, Jennifer Cole 0001	INTERSPEECH	1
2016	New release of Mixer-6: Improved validity for phonetic study of speaker variation and identification Eleanor Chodroff, Matthew Maciejewski, Jan Trmal, Sanjeev Khudanpur, John Godfrey	LREC	1