Textless Speech-to-Speech Translation on Real Data

Keyphrases

• S2ST 100%
• Speech Translation 100%
• Speaker Normalization 33%
• Normalization Method 16%
• Language Pair 16%
• Text Data 16%
• Audio 16%
• Single Reference 16%
• Lexical Content 16%
• Paired Data 16%
• Unit-based 16%
• Multiple Languages 16%
• Speech Encoder 16%
• Multi-speaker 16%
• Multiple Speakers 16%
• Un-normalized 16%
• Target Speech 16%

Computer Science

• Speech Normalization 100%
• Single Reference 50%
• Multiple Language 50%