Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment.
Joseph LiuMahesh Kumar NandwanaJanne PylkkönenHannes HeikinheimoMorgan McGuirePublished in: CoRR (2024)
Keyphrases
- text to speech
- multi lingual
- voice activity detection
- text to speech synthesis
- speech synthesis
- text recognition
- false positives
- synthesized speech
- emotion recognition
- text input
- lexical features
- text generation
- information retrieval
- detection algorithm
- english text
- text retrieval
- language independent
- detection method
- object detection
- natural language generation
- word level
- complex background
- speech recognition
- digital libraries
- multimodal interaction
- noisy environments
- speech signal
- text documents