SLP-L20.6

T-CACHE: FAST INFERENCE FOR MASKED GENERATIVE TRANSFORMER-BASED TTS VIA PROMPT-AWARE FEATURE CACHING

Obed Irihose, Le Zhang, University of Electronic Science and Technology of China, China
Session:
SLP-L20: Streaming and Efficient TTS Systems Oral
Track:
Speech and Language Processing [SL]
Location:
Room 114
Presentation Time:
Fri, 8 May, 15:40 - 16:00
Presentation
Discussion
Resources
No resources available.
Session SLP-L20
SLP-L20.1: VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency
Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze, KTH Royal Institute of Technology, Sweden
SLP-L20.2: SYNCSPEECH: EFFICIENT AND LOW-LATENCY TEXT-TO-SPEECH BASED ON TEMPORAL MASKED TRANSFORMER
Zhengyan Sheng, University of Science and Technology of China, China; Zhihao Du, Shiliang Zhang, Zhijie Yan, Independent Researcher, China; Liping Chen, University of Science and Technology of China, China
SLP-L20.3: RETRIEVAL-BASED SPECULATIVE DECODING FOR AUTOREGRESSIVE SPEECH SYNTHESIS
Alan Chi-Man Lee, The Chinese University of Hong Kong, Hong Kong; Wing-Sun Cheng, RISKSIS, Hong Kong; Calvin Chun-Kit Chan, The Chinese University of Hong Kong, Hong Kong
SLP-L20.4: PRINCIPLED COARSE-GRAINED ACCEPTANCE FOR SPECULATIVE DECODING IN SPEECH
Moran Yanuka, Apple, Tel-Aviv University, Israel; Paul Dixon, Eyal Finkelshtein, Daniel Rotman, Apple, Switzerland; Raja Giryes, Tel-Aviv University, Israel
SLP-L20.5: SPADE: STRUCTURED PRUNING AND ADAPTIVE DISTILLATION FOR EFFICIENT LLM-TTS
Tan Dat Nguyen, Jaehun Kim, Ji-Hoon Kim, Korea Advanced Institute of Science and Technology, Korea, Republic of; Shukjae Choi, Youshin Lim, 42dot Inc, Korea, Republic of; Joon Son Chung, Korea Advanced Institute of Science and Technology, Korea, Republic of
SLP-L20.6: T-CACHE: FAST INFERENCE FOR MASKED GENERATIVE TRANSFORMER-BASED TTS VIA PROMPT-AWARE FEATURE CACHING
Obed Irihose, Le Zhang, University of Electronic Science and Technology of China, China
Contacts