Enhancing Speech Emotion Recognition Leveraging Aligning Timestamps of ASR Transcripts and Speaker Diarization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Hsuan-Yu, Lee, Pei-Ying, Chen, Berlin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912501249081344
author Wang, Hsuan-Yu
Lee, Pei-Ying
Chen, Berlin
author_facet Wang, Hsuan-Yu
Lee, Pei-Ying
Chen, Berlin
contents In this paper, we investigate the impact of incorporating timestamp-based alignment between Automatic Speech Recognition (ASR) transcripts and Speaker Diarization (SD) outputs on Speech Emotion Recognition (SER) accuracy. Misalignment between these two modalities often reduces the reliability of multimodal emotion recognition systems, particularly in conversational contexts. To address this issue, we introduce an alignment pipeline utilizing pre-trained ASR and speaker diarization models, systematically synchronizing timestamps to generate accurately labeled speaker segments. Our multimodal approach combines textual embeddings extracted via RoBERTa with audio embeddings from Wav2Vec, leveraging cross-attention fusion enhanced by a gating mechanism. Experimental evaluations on the IEMOCAP benchmark dataset demonstrate that precise timestamp alignment improves SER accuracy, outperforming baseline methods that lack synchronization. The results highlight the critical importance of temporal alignment, demonstrating its effectiveness in enhancing overall emotion recognition accuracy and providing a foundation for robust multimodal emotion analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19356
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Speech Emotion Recognition Leveraging Aligning Timestamps of ASR Transcripts and Speaker Diarization
Wang, Hsuan-Yu
Lee, Pei-Ying
Chen, Berlin
Computation and Language
Sound
Audio and Speech Processing
I.2.7; I.5.1
In this paper, we investigate the impact of incorporating timestamp-based alignment between Automatic Speech Recognition (ASR) transcripts and Speaker Diarization (SD) outputs on Speech Emotion Recognition (SER) accuracy. Misalignment between these two modalities often reduces the reliability of multimodal emotion recognition systems, particularly in conversational contexts. To address this issue, we introduce an alignment pipeline utilizing pre-trained ASR and speaker diarization models, systematically synchronizing timestamps to generate accurately labeled speaker segments. Our multimodal approach combines textual embeddings extracted via RoBERTa with audio embeddings from Wav2Vec, leveraging cross-attention fusion enhanced by a gating mechanism. Experimental evaluations on the IEMOCAP benchmark dataset demonstrate that precise timestamp alignment improves SER accuracy, outperforming baseline methods that lack synchronization. The results highlight the critical importance of temporal alignment, demonstrating its effectiveness in enhancing overall emotion recognition accuracy and providing a foundation for robust multimodal emotion analysis.
title Enhancing Speech Emotion Recognition Leveraging Aligning Timestamps of ASR Transcripts and Speaker Diarization
topic Computation and Language
Sound
Audio and Speech Processing
I.2.7; I.5.1
url https://arxiv.org/abs/2507.19356