Can Emotion Fool Anti-spoofing?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912403669647360 |
|---|---|
| author | Mahapatra, Aurosweta Ulgen, Ismail Rasim Naini, Abinay Reddy Busso, Carlos Sisman, Berrak |
| author_facet | Mahapatra, Aurosweta Ulgen, Ismail Rasim Naini, Abinay Reddy Busso, Carlos Sisman, Berrak |
| contents | Traditional anti-spoofing focuses on models and datasets built on synthetic speech with mostly neutral state, neglecting diverse emotional variations. As a result, their robustness against high-quality, emotionally expressive synthetic speech is uncertain. We address this by introducing EmoSpoof-TTS, a corpus of emotional text-to-speech samples. Our analysis shows existing anti-spoofing models struggle with emotional synthetic speech, exposing risks of emotion-targeted attacks. Even trained on emotional data, the models underperform due to limited focus on emotional aspect and show performance disparities across emotions. This highlights the need for emotion-focused anti-spoofing paradigm in both dataset and methodology. We propose GEM, a gated ensemble of emotion-specialized models with a speech emotion recognition gating network. GEM performs effectively across all emotions and neutral state, improving defenses against spoofing attacks. We release the EmoSpoof-TTS Dataset: https://emospoof-tts.github.io/Dataset/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23962 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can Emotion Fool Anti-spoofing? Mahapatra, Aurosweta Ulgen, Ismail Rasim Naini, Abinay Reddy Busso, Carlos Sisman, Berrak Audio and Speech Processing Machine Learning Sound Traditional anti-spoofing focuses on models and datasets built on synthetic speech with mostly neutral state, neglecting diverse emotional variations. As a result, their robustness against high-quality, emotionally expressive synthetic speech is uncertain. We address this by introducing EmoSpoof-TTS, a corpus of emotional text-to-speech samples. Our analysis shows existing anti-spoofing models struggle with emotional synthetic speech, exposing risks of emotion-targeted attacks. Even trained on emotional data, the models underperform due to limited focus on emotional aspect and show performance disparities across emotions. This highlights the need for emotion-focused anti-spoofing paradigm in both dataset and methodology. We propose GEM, a gated ensemble of emotion-specialized models with a speech emotion recognition gating network. GEM performs effectively across all emotions and neutral state, improving defenses against spoofing attacks. We release the EmoSpoof-TTS Dataset: https://emospoof-tts.github.io/Dataset/ |
| title | Can Emotion Fool Anti-spoofing? |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2505.23962 |