M5-TTS:A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi Token Prediction
ASLP-lab
ASLP-lab
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
ASLP-lab/DRAMA-Eval liked a dataset 1 day ago
ASLP-lab/DRAMA-Eval updated a collection 2 days ago
M5-TTSOrganizations
None yet
Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
An instruct text-to-speech model developed by ASLP.
a large-scale open-source corpus with a full processing pipeline and benchmarks for ASR and TTS
OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.
M5-TTS:A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi Token Prediction
Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
Low Frame Rate Universal Audio Codec with Semantic–Acoustic Disentanglement
YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
An instruct text-to-speech model developed by ASLP.
a large-scale open-source corpus with a full processing pipeline and benchmarks for ASR and TTS
A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation
OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.