Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

What You Feel Is Not What They See: On Predicting Self-Reported Emotion from Third-Party Observer Labels

Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

Authors:Yara El-Tawil*, Aneesha Sampath*, Emily Mower Provost

Self-reported emotion labels capture internal experience, while third-party labels reflect external perception. These perspectives often diverge, limiting the applicability of third-party-trained models to self-report contexts. This gap is critical in mental health, where accurate self-report modeling is essential for guiding intervention. We present the first cross-corpus evaluation of third-party-trained models on self-reports. We find activation unpredictable (CCC approximately 0) and valence moderately predictable (CCC approximately 0.3). Crucially, when content is personally significant to the speaker, models achieve high performance for valence (CCC approximately 0.6-0.8). Our findings point to personal significance as a key pathway for aligning external perception with internal experience and underscore the challenge of self-report activation modeling.

SEER: The Span-based Emotion Evidence Retrieval Benchmark

Published in The 14th International Joint Conference on Natural Language Processing and the 4rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

Authors:Aneesha Sampath, Oya Aran, Emily Mower Provost

We introduce the SEER (Span-based Emotion Evidence Retrieval) Benchmark to test Large Language Models’ (LLMs) ability to identify the specific spans of text that express emotion. Unlike traditional emotion recognition tasks that assign a single label to an entire sentence, SEER targets the underexplored task of emotion evidence detection: pinpointing which exact phrases convey emotion. This span-level approach is crucial for applications like empathetic dialogue and clinical support, which need to know how emotion is expressed, not just what the emotion is. SEER includes two tasks: identifying emotion evidence within a single sentence, and identifying evidence across a short passage of five consecutive sentences. It contains new annotations for both emotion and emotion evidence on 1200 real-world sentences. We evaluate 14 open-source LLMs and find that, while some models approach average human performance on single-sentence inputs, their accuracy degrades in longer passages. Our error analysis reveals key failure modes, including overreliance on emotion keywords and false positives in neutral text.

Efficient Finetuning for Dimensional Speech Emotion Recognition in the Age of Transformers

Published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025

Authors:Aneesha Sampath*, James Tavernor*, Emily Mower Provost

Accurate speech emotion recognition is essential for developing human-facing systems. Recent advancements have included finetuning large, pretrained transformer models like Wav2Vec 2.0. However, the finetuning process requires substantial computational resources, including high-memory GPUs and significant processing time. As the demand for accurate emotion recognition continues to grow, efficient finetuning approaches are needed to reduce the computational burden. Our study focuses on dimensional emotion recognition, predicting attributes such as activation (calm to excited) and valence (negative to positive). We present various finetuning techniques, including full finetuning, partial finetuning of transformer layers, finetuning with mixed precision, partial finetuning with caching, and low-rank adaptation (LoRA) on the Wav2Vec 2.0 base model. We find that partial finetuning with mixed precision achieves performance comparable to full finetuning while increasing training speed by 67%. Caching intermediate representations further boosts efficiency, yielding an 88% speedup and a 71% reduction in learnable parameters. We recommend finetuning the final three transformer layers in mixed precision to balance performance and training efficiency, and adding intermediate representation caching for optimal speed with minimal performance trade-offs. These findings lower the barriers to finetuning speech emotion recognition systems, making accurate emotion recognition more accessible to a broader range of researchers and practitioners.

Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models

Published in Interspeech, 2024

Authors:Matthew Perez, Aneesha Sampath, Minxue Niu, Emily Mower Provost

Aphasia is a language disorder that can lead to speech errors known as paraphasias, which involve the misuse, substitution, or invention of words. Automatic paraphasia detection can help those with Aphasia by facilitating clinical assessment and treatment planning options. However, most automatic paraphasia detection works have focused solely on binary detection, which involves recognizing only the presence or absence of a paraphasia. Multiclass paraphasia detection represents an unexplored area of research that focuses on identifying multiple types of paraphasias and where they occur in a given speech segment. We present novel approaches that use a generative pretrained transformer (GPT) to identify paraphasias from transcripts as well as two end-to-end approaches that focus on modeling both automatic speech recognition (ASR) and paraphasia classification as multiple sequences vs. a single sequence. We demonstrate that a single sequence model outperforms GPT baselines for multiclass paraphasia detection.

Workshops

SeedBERT: Recovering Annotator Rating Distributions from an Aggregated Label

Published in AAAI Workshop on Uncertainty Reasoning and Quantification in Decision Making, 2023

Authors:Aneesha Sampath, Victoria Lin, Louis-Philippe Morency

Many machine learning tasks – particularly those in affective computing – are inherently subjective. When asked to classify facial expressions or to rate an individual’s attractiveness, humans may disagree with one another, and no single answer may be objectively correct. However, machine learning datasets commonly have just one ‘ground truth’ label for each sample, so models trained on these labels may not perform well on tasks that are subjective in nature. Though allowing models to learn from the individual annotators’ ratings may help, most datasets do not provide annotator-specific labels for each sample. To address this issue, we propose SeedBERT, a method for recovering annotator rating distributions from a single label by inducing pre-trained models to attend to different portions of the input. Our human evaluations indicate that SeedBERT’s attention mechanism is consistent with human sources of annotator disagreement. Moreover, in our empirical evaluations using large language models, SeedBERT demonstrates substantial gains in performance on downstream subjective tasks compared both to standard deep learning models and to other current models that account explicitly for annotator disagreement.