Papers › Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization
Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization
Benjamin Milde, Chris Biemann
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding pseudo-posteriorgrams. The degree of sparsity in this posteriorgram can be fully controlled after the model has been trained. We use the Gumbel-Softmax trick to approximately sample from a discrete distribution in the neural network and this allows us to train the network efficiently with standard backpropagation. The new and improved model is trained and evaluated on the Libri-Light corpus, a benchmark for ASR with limited or no supervision. The model is trained on 600h and 6000h of English read speech. We evaluate the improved model using the ABX error measure and a semi-supervised setting with 10h of transcribed speech. We observe a relative improvement of up to 31.4% on ABX error rates across speakers on the test set with the improved Sparsespeech model on 600h of speech data and further improvements when we scale the model to 6000h.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Recognition | Libri-Light test-clean | S6000h-n42-τ2 → 0.1 | ABX-across | 13.53 | #5 of 5 | Archive leaderboard | report |
| Speech Recognition | Libri-Light test-clean | S6000h-n42-τ2 → 0.1 | ABX-within | 9.33 | #5 of 5 | Archive leaderboard | report |
| Speech Recognition | Libri-Light test-other | S6000h-n42-τ2 → 0.1 | ABX-across | 20.6 | #5 of 5 | Archive leaderboard | report |
| Speech Recognition | Libri-Light test-other | S6000h-n42-τ2 → 0.1 | ABX-within | 12.05 | #5 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections