Multimodal multi-label emotion recognition is important for affect-aware systems, but models trained with complete text, visual, and acoustic streams often degrade sharply when some streams are unavailable at deployment. We address this train-test gap by learning a compact representation that preserves emotion-specific...
Chuang-Xin Zhao, Mei-Mei Zhang, Can-Ran Xiao et al.· 0 citations
We present the results of the VoiceMOS Challenge 2026, the fifth edition of a scientific challenge on automatic prediction of subjective speech assessments. After expanding the scope to music and general audio in 2025, we refocused the evaluation target on speech and organized three tracks: prediction of absolute and c...
Wen-Chin Huang, Wei Wang, Marvin Sach et al.· 0 citations
Speech watermarking offers proactive traceability for synthetic speech, yet most existing models operate only after text-to-speech (TTS) synthesis by adding a watermark perturbation to the generated waveform. This post-hoc design leaves watermarking as an external step that can be omitted or bypassed and restricts the...
Audio watermarking is increasingly important for tracing generated speech. Several audio watermarking methods have been proposed to embed the watermark in various domains, such as waveform, timbre feature, or latent representations, for making the embedded watermark robust against traditional digital signal processing...
ART-NAD is proposed, a reference-audio intelligibility metric that replaces the vocal-tract constriction variables of NAD with vocal-tract constriction variables predicted from audio by a speaker-independent acoustic-to-articulatory inversion model trained on the same \texttt{wav2vec2} features.
B. Halpern, Thomas B. Tienkamp, D. Abur et al.· 0 citations
This study proposes transcription quality labels (TQL), automatically derived from connectionist temporal classification scores, and confirms that synthesis quality varies systematically with TQL values at inference, demonstrating learned quality-conditioned behavior.
Pseudo-label distillation not only transfers the performance of SSL models to a compact model but also further improves performance by leveraging available coarse labels and data augmentation.
Takuya Fujimura, Tomoki Toda· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
