Unsupervised Speech Recognition
7 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Unsupervised Speech Recognition
Libraries
Use these libraries to find Unsupervised Speech Recognition models and implementationsMost implemented papers
A segmental framework for fully-unsupervised large-vocabulary speech recognition
We also show that the discovered clusters can be made less speaker- and gender-specific by using an unsupervised autoencoder-like feature extractor to learn better frame-level features (prior to embedding).
Unsupervised Speech Recognition
pytorch/fairseq
•
•
NeurIPS 2021
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe.
Towards End-to-end Unsupervised Speech Recognition
pytorch/fairseq
•
•
Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language.
Supervised Acoustic Embeddings And Their Transferability Across Languages
In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings.
A Theory of Unsupervised Speech Recognition
cactuswiththoughts/unsupasrtheory
•
•
Unsupervised speech recognition (ASR-U) is the problem of learning automatic speech recognition (ASR) systems from unpaired speech-only and text-only corpora.
Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching
Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands.
Towards Unsupervised Speech Recognition Without Pronunciation Models
jeromeni/wholeword-uasr-jstti
•
•
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora.
