5 papers
Can Emotion Fool Anti-spoofing?
Aurosweta Mahapatra, Ismail Rasim Ulgen, Abinay Reddy Naini +2
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…
EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast
Shreeram Suresh Chandra, Lucas Goncalves, Junchen Lu +2
Current emotion-based contrastive language-audio pretraining (CLAP) methods typically learn by naïvely aligning audio samples with corresponding text prompts. Consequently, this ap…
Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset
Rui Liu, Pu Gao, Jiatian Xi +3
Text-based speech editing (TSE) modifies speech using only text, eliminating re-recording. However, existing TSE methods, mainly focus on the content accuracy and acoustic consiste…
Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline
Ali N. Salman, Zongyang Du, Shreeram Suresh Chandra +3
Voice conversion (VC) research traditionally depends on scripted or acted speech, which lacks the natural spontaneity of real-life conversations. While natural speech data is limit…
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
Mirazul Haque, Rutvij Shah, Simin Chen +3
Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real…