Improving Automated Speech Recognition Using Retrieval-Based Voice Conversion.
Anas Mohammed AlhumudMuhammad Al-QurishiYasser Omar AlomarAli AlzahraniRiad SouissiPublished in: Tiny Papers @ ICLR (2024)
Keyphrases
- text to speech
- emotion recognition
- speech synthesis
- speech recognition
- information retrieval
- speech quality
- semi automated
- information retrieval systems
- voice activity detection
- speech recognition errors
- retrieval systems
- image database
- speech sounds
- speech signal
- fundamental frequency
- text to speech synthesis
- image retrieval
- audio visual
- retrieval method
- multimedia databases
- text retrieval
- retrieval model
- test collection
- relevance feedback
- retrieval accuracy
- spoken language
- speaker verification
- vocal tract
- content based video retrieval
- lead to significant improvements
- human computer interaction
- probabilistic model