Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models
Not on the map. Why?
Abstract (arXiv)
Large language models (LLMs) have started to play a vital role in modelling speech and text. To explore the best use of context and multiple systems' outputs for post-ASR speech emotion prediction, we study LLM prompting on a recent task named GenSEC. Our techniques include ASR transcript ranking, variable conversation context, and system output fusion. We show that the conversation context has diminishing returns and the metric used to select the transcript for prediction is crucial. Finally, our best submission surpasses the provided baseline by 20% in absolute accuracy.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 4 Oct 2024.
Builds on
11 of 18 references.
References · 11
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
- 2020Multi-modal Attention for Speech Emotion Recognitioncited by 29
- 2021Fusing ASR Outputs in Joint Training for Speech Emotion Recognitioncited by 21
- 2023Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmentingcited by 17
- 2024Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniquescited by 15
- 2024Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognitioncited by 10
- 2024Crossmodal ASR Error Correction with Discrete Speech Unitscited by 9
- 2023LanSER: Language-Model Supported Speech Emotion Recognitioncited by 5
- 2021The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translationcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.