Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386907347> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4386907347 abstract "In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS. First, we investigated the representation ability of different speech self-supervised pre-trained models, and we found that data2vec has a good representation ability on the SER task. Second, we employed a powerful large language model (LLM), GPT-4, and emotional text-to-speech (TTS) model, Azure TTS, to generate emotionally congruent text and speech. We carefully designed the text prompt and dataset construction, to obtain the synthetic emotional speech data with high quality. Third, we studied different ways of data augmentation to promote the SER task with synthetic speech, including random mixing, adversarial training, transfer learning, and curriculum learning. Experiments and ablation studies on the IEMOCAP dataset demonstrate the effectiveness of our method, compared with other data augmentation methods, and data augmentation with other synthetic data." @default.
- W4386907347 created "2023-09-21" @default.
- W4386907347 creator A5007473150 @default.
- W4386907347 creator A5026563375 @default.
- W4386907347 creator A5055433405 @default.
- W4386907347 creator A5068290128 @default.
- W4386907347 creator A5068357345 @default.
- W4386907347 creator A5074750047 @default.
- W4386907347 creator A5077593507 @default.
- W4386907347 date "2023-09-18" @default.
- W4386907347 modified "2023-09-27" @default.
- W4386907347 title "Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition" @default.
- W4386907347 doi "https://doi.org/10.48550/arxiv.2309.10294" @default.
- W4386907347 hasPublicationYear "2023" @default.
- W4386907347 type Work @default.
- W4386907347 citedByCount "0" @default.
- W4386907347 crossrefType "posted-content" @default.
- W4386907347 hasAuthorship W4386907347A5007473150 @default.
- W4386907347 hasAuthorship W4386907347A5026563375 @default.
- W4386907347 hasAuthorship W4386907347A5055433405 @default.
- W4386907347 hasAuthorship W4386907347A5068290128 @default.
- W4386907347 hasAuthorship W4386907347A5068357345 @default.
- W4386907347 hasAuthorship W4386907347A5074750047 @default.
- W4386907347 hasAuthorship W4386907347A5077593507 @default.
- W4386907347 hasBestOaLocation W43869073471 @default.
- W4386907347 hasConcept C14999030 @default.
- W4386907347 hasConcept C154945302 @default.
- W4386907347 hasConcept C162324750 @default.
- W4386907347 hasConcept C17744445 @default.
- W4386907347 hasConcept C187736073 @default.
- W4386907347 hasConcept C199539241 @default.
- W4386907347 hasConcept C204321447 @default.
- W4386907347 hasConcept C2776359362 @default.
- W4386907347 hasConcept C2777438025 @default.
- W4386907347 hasConcept C2780451532 @default.
- W4386907347 hasConcept C28490314 @default.
- W4386907347 hasConcept C41008148 @default.
- W4386907347 hasConcept C94625758 @default.
- W4386907347 hasConceptScore W4386907347C14999030 @default.
- W4386907347 hasConceptScore W4386907347C154945302 @default.
- W4386907347 hasConceptScore W4386907347C162324750 @default.
- W4386907347 hasConceptScore W4386907347C17744445 @default.
- W4386907347 hasConceptScore W4386907347C187736073 @default.
- W4386907347 hasConceptScore W4386907347C199539241 @default.
- W4386907347 hasConceptScore W4386907347C204321447 @default.
- W4386907347 hasConceptScore W4386907347C2776359362 @default.
- W4386907347 hasConceptScore W4386907347C2777438025 @default.
- W4386907347 hasConceptScore W4386907347C2780451532 @default.
- W4386907347 hasConceptScore W4386907347C28490314 @default.
- W4386907347 hasConceptScore W4386907347C41008148 @default.
- W4386907347 hasConceptScore W4386907347C94625758 @default.
- W4386907347 hasLocation W43869073471 @default.
- W4386907347 hasOpenAccess W4386907347 @default.
- W4386907347 hasPrimaryLocation W43869073471 @default.
- W4386907347 hasRelatedWork W1513802107 @default.
- W4386907347 hasRelatedWork W1567113014 @default.
- W4386907347 hasRelatedWork W1977886375 @default.
- W4386907347 hasRelatedWork W2081647779 @default.
- W4386907347 hasRelatedWork W2293457016 @default.
- W4386907347 hasRelatedWork W2557907115 @default.
- W4386907347 hasRelatedWork W2789919619 @default.
- W4386907347 hasRelatedWork W3169305685 @default.
- W4386907347 hasRelatedWork W4237750775 @default.
- W4386907347 hasRelatedWork W4321365464 @default.
- W4386907347 isParatext "false" @default.
- W4386907347 isRetracted "false" @default.
- W4386907347 workType "article" @default.