How to Leverage Synthetic Speech for LLM-Based ASR Systems? 文章
ArXiv CS.CL2026-07-10PAPERen作者: Yanis Labrak, Dairazalia Sanchez-Cortes, Sergio Burdisso, S\'everin Baroudi, Shashi Kumar, Esa\'u Villatoro-Tello, Srikanth Madikeri, Manjunath K E, Old\v{r}ich Plchot, Kadri Hacio\u{g}lu, Petr Motlicek, Andreas Stolcke
How to Leverage Synthetic Speech for LLM-Based ASR Systems? · 相关技术
相关技术
LLMautomatic speech recognitionACTACEABIAMD EXPOANNAPPSARCARGASRATEAdaptive Batch ScalingAlternative Uses TestAugmented Latent IntrinsicsAutomatic Text ScoringAutoregressive large language modelsAuxiliary Regression LossBlurry Window AttentionCOGCTLCTUCausal Agent ReplayComposed Object RetrievalComprehensive Spatial-Temporal Representation Learning FrameworkDINDIRDIRECTDIffusion Reconstruction ErrorDOMDeep Image CompressionDensity-Aware TranslationECTEfficient Majority-then-StoppingEmpirical Privacy AuditingEquilibrium State EstimationEvidence Dilution IndexFacial Affect RecognitionSLAM-ASR