Weakly Supervised Multi-Embeddings Learning of Acoustic Models

Emmanuel Dupoux; Gabriel Synnaeve

Weakly Supervised Multi-Embeddings Learning of Acoustic Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1412.6645 v3 pith:VRPPXWBR submitted 2014-12-20 cs.SD cs.CLcs.LG

Gabriel Synnaeve , Emmanuel Dupoux This is my paper · ORCID

classification cs.SDcs.CLcs.LG

keywords differentsamediscriminatenetworkacousticdatasetfirstfound

verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments

read the original abstract

We trained a Siamese network with multi-task same/different information on a speech dataset, and found that it was possible to share a network for both tasks without a loss in performance. The first task was to discriminate between two same or different words, and the second was to discriminate between two same or different talkers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling
eess.AS 2019-08 conditional novelty 5.0 of 10

A multi-task bottleneck feature system that combines unsupervised clustering labels and out-of-domain ASR labels matches the best ZeroSpeech 2017 across-speaker ABX error of 9.7%.

Pith tools