A data pipeline, 14-dimension benchmark, and decoupled fine-tuning model are presented to advance fine-grained multi-dimensional speech understanding in LLMs.
Wenetspeech-yue: A large-scale cantonese speech corpus with multi-dimensional annotation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
A data pipeline, 14-dimension benchmark, and decoupled fine-tuning model are presented to advance fine-grained multi-dimensional speech understanding in LLMs.