In a large production dataset, the Google STT plus GPT-4.1 plus Cartesia TTS interview stack outperformed four alternatives, while LLM-judged quality correlated weakly with user satisfaction.
Lslm: A listening while speaking language model for real-time full-duplex dialogue
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Evaluating Speech-to-Text x LLM x Text-to-Speech Combinations for AI Interview Systems
In a large production dataset, the Google STT plus GPT-4.1 plus Cartesia TTS interview stack outperformed four alternatives, while LLM-judged quality correlated weakly with user satisfaction.