When Less Is More? Diagnosing ASR Predictions in Sardinian via Layer-Wise Decoding

Documenti analoghi

• Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs
  di: De Cristofaro, Domenico, et al.
  Pubblicazione: (2025)
• Languages in Whisper-Style Speech Encoders Align Both Phonetically and Semantically
  di: Shim, Ryan Soh-Eun, et al.
  Pubblicazione: (2025)
• Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
  di: Wang, Xinyu, et al.
  Pubblicazione: (2026)
• Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More
  di: Philippy, Fred, et al.
  Pubblicazione: (2024)
• When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation
  di: Kapur, Rhea, et al.
  Pubblicazione: (2026)