Search Results for author:
Found 2 papers, 1 papers with code
Probing Acoustic Representations for Phonetic Properties
Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited.
Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs
Paraphrases are important linguistic resources for a wide variety of NLP applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
