Search papers, labs, and topics across Lattice.
6
0
6
42
Segments with conflicting quality signals are systematically undervalued, revealing critical flaws in current evaluation metrics for multilingual tasks.
Indic DiarBench reveals that existing ASR systems struggle with the rich linguistic diversity of Indian languages, highlighting a critical gap in multilingual speech technology.
Evaluating AudioLLMs reveals that many models fail to leverage contextual information effectively, challenging assumptions about their pretraining capabilities.
Forget English – this study reveals which TTS systems truly resonate with native speakers across ten diverse Indian languages, pinpointing specific perceptual dimensions that drive preference.
VLM evaluators, despite their growing use, can miss over 50% of targeted errors in generated images and text, especially when those errors involve fine-grained details or spatial relationships.
Current ASR systems stumble significantly when faced with the nuances of real-world Indian speech, as revealed by a new benchmark exposing geographic performance disparities and the impact of audio quality, speaking rate, and device type.
