3 papers
cs.SD2025
Spatial-CLAP: Learning Spatially-Aware audio--text Embeddings for Multi-Source Conditions
Kentaro Seki, Yuki Okamoto, Kouei Yamaoka +3
Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-sour…
cs.SD2025
AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences
Minoru Kishi, Ryosuke Sakai, Shinnosuke Takamichi +2
We propose a novel objective evaluation metric for synthesized audio in text-to-audio (TTA), aiming to improve the performance of TTA models. In TTA, subjective evaluation of the s…
cs.SD2025
RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio
Yusuke Kanamori, Yuki Okamoto, Taisei Takano +3
In text-to-audio (TTA) research, the relevance between input text and output audio is an important evaluation aspect. Traditionally, it has been evaluated from both subjective and…