Search papers, labs, and topics across Lattice.
3
0
6
10
V\={a}kQA, a Telugu SQA benchmark of 2,001 factoid question-answer pairs across six domains, is introduced and it is observed that Telugu phrasing retains cultural specificity that is lost in translation, speech input introduces phonetic confusions that alter question meaning, and cascaded ASR-MT errors compound progressively.
Speaker conditioning via FiLM can enhance ASR performance for pathological speech without compromising standard speech recognition capabilities.
Multilingual and multimodal embeddings leak way more lexical information than you think – FLiP can recover 75% of the original text.
