Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching
This work addresses challenges in unsupervised speech recognition for researchers, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackled unsupervised speech recognition by introducing ESPUM, which uses N-skipgrams and positional unigram matching to address GAN instability and misalignment issues, achieving competitive performance on the TIMIT benchmark.
Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.