CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909916531261440 |
|---|---|
| author | Ning, Jinzhong Tulajiang, Paerhati Le, Yingying Zhang, Yijia Sun, Yuanyuan Lin, Hongfei Liu, Haifeng |
| author_facet | Ning, Jinzhong Tulajiang, Paerhati Le, Yingying Zhang, Yijia Sun, Yuanyuan Lin, Hongfei Liu, Haifeng |
| contents | Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover, existing models also suffer from rigid single-order generation templates and weak semantic alignment, substantially limiting their performance. To address these challenges, we introduce CommonVoice-SpeechRE, a large-scale dataset comprising nearly 20,000 real-human speech samples from diverse speakers, establishing a new benchmark for SpeechRE research. Furthermore, we propose the Relation Prompt-Guided Multi-Order Generative Ensemble (RPG-MoGe), a novel framework that features: (1) a multi-order triplet generation ensemble strategy, leveraging data diversity through diverse element orders during both training and inference, and (2) CNN-based latent relation prediction heads that generate explicit relation prompts to guide cross-modal alignment and accurate triplet generation. Experiments show our approach outperforms state-of-the-art methods, providing both a benchmark dataset and an effective solution for real-world SpeechRE. The source code and dataset are publicly available at https://github.com/NingJinzhong/SpeechRE_RPG_MoGe. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework Ning, Jinzhong Tulajiang, Paerhati Le, Yingying Zhang, Yijia Sun, Yuanyuan Lin, Hongfei Liu, Haifeng Computation and Language Multimedia Sound Audio and Speech Processing Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover, existing models also suffer from rigid single-order generation templates and weak semantic alignment, substantially limiting their performance. To address these challenges, we introduce CommonVoice-SpeechRE, a large-scale dataset comprising nearly 20,000 real-human speech samples from diverse speakers, establishing a new benchmark for SpeechRE research. Furthermore, we propose the Relation Prompt-Guided Multi-Order Generative Ensemble (RPG-MoGe), a novel framework that features: (1) a multi-order triplet generation ensemble strategy, leveraging data diversity through diverse element orders during both training and inference, and (2) CNN-based latent relation prediction heads that generate explicit relation prompts to guide cross-modal alignment and accurate triplet generation. Experiments show our approach outperforms state-of-the-art methods, providing both a benchmark dataset and an effective solution for real-world SpeechRE. The source code and dataset are publicly available at https://github.com/NingJinzhong/SpeechRE_RPG_MoGe. |
| title | CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework |
| topic | Computation and Language Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.08438 |