Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
Muyang Du, Jason Roche, Junjie Lai
Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TT…
cs.SD2024
Incremental FastPitch: Chunk-based High Quality Text to Speech
Muyang Du, Chuan Liu, Junjie Lai
Parallel text-to-speech models have been widely applied for real-time speech synthesis, and they offer more controllability and a much faster synthesis process compared with conven…