Pith. sign in

REVIEW 3 cited by

L-Vector: Neural Label Embedding for Domain Adaptation

Not yet reviewed by Pith; the record is open.

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 2004.13480 v1 pith:FNBHMULD submitted 2020-04-25 eess.AS cs.CLcs.LGcs.SDstat.ML

classification eess.AScs.CLcs.LGcs.SDstat.ML
keywords datalabeladaptationhoursmodelneuralsource-domainacoustic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains. With NLE method, we distill the knowledge from a powerful source-domain DNN into a dictionary of label embeddings, or l-vectors, one for each senone class. Each l-vector is a representation of the senone-specific output distributions of the source-domain DNN and is learned to minimize the average L2, Kullback-Leibler (KL) or symmetric KL distance to the output vectors with the same label through simple averaging or standard back-propagation. During adaptation, the l-vectors serve as the soft targets to train the target-domain model with cross-entropy loss. Without parallel data constraint as in the teacher-student learning, NLE is specially suited for the situation where the paired target-domain data cannot be simulated from the source-domain data. We adapt a 6400 hours multi-conditional US English acoustic model to each of the 9 accented English (80 to 830 hours) and kids' speech (80 hours). NLE achieves up to 14.1% relative word error rate reduction over direct re-training with one-hot labels.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Automata Learning -- Expect Delays!

    cs.FL 2025-08 conditional novelty 7.0 of 10

    A two-stage active learning method for Mealy machines with stochastic transition delays uses learned structure to plan efficient delay sampling, outperforming naive sampling-based L*.

  2. Simple Nash Equilibria for Qualitative Multiplayer Games

    cs.GT 2026-07 conditional novelty 6.0 of 10

    Memoryless randomised subgame-perfect equilibria always exist for turn-based deterministic games with reachability, safety, and 0-2 Muller objectives, and can be constructed in polynomial time.

  3. Simplicity Lies in the Eye of the Beholder: A Strategic Perspective on Controllers in Reactive Synthesis

    cs.LO 2025-09 accept novelty 3.0 of 10

    A survey of memory and randomness complexity for strategies in reactive synthesis, arguing that Mealy-machine-based measures of simplicity are representation-dependent.

Pith tools