Search papers, labs, and topics across Lattice.
Friedrich-Alexander-Universität Erlangen-Nürnberg
2
0
4
Ditch phoneme-based speech processing: directly predicting phonological features from speech unlocks substantial gains in multilingual and cross-lingual speech recognition.
Wav2Vec 2.0, despite boosting accuracy in speech-based cognitive impairment detection, introduces significant gender and age biases, misclassifying females and younger individuals at a higher rate.
