wav-2vec 2.0
Emerging5papers using it
2021first seen
Wav2vec 2.0 is a speech representation model used to evaluate the performance of fine-tuned speech models across various tasks while maintaining cross-task generalization.
Papers using wav-2vec 2.0 (5)
- StableQuant: Layer Adaptive Post-Training Quantization for Speech
Foundation ModelsSpeech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task GeneralizationSTC speaker recognition systems for the NIST SRE 2021Do We Still Need Automatic Speech Recognition for Spoken Language
Understanding?Benchmarking Children's ASR with Supervised and Self-supervised Speech
Foundation Models