MétaCan
Menu
Back to cohort
Record W4288087689 · doi:10.48550/arxiv.1910.13923

Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank\n Transformer

2019· preprint· en· W4288087689 on OpenAlexaff
Genta Indra Winata, Samuel Cahyawijaya, Zhaojiang Lin, Zihan Liu, Pascale Fung

Bibliographic record

VenuearXiv (Cornell University) · 2019
Typepreprint
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsTransformerEnd-to-end principleInferenceComputer scienceLanguage modelSoftware deploymentArtificial neural networkSpeech recognitionArtificial intelligenceEngineering

Abstract

fetched live from OpenAlex

Highly performing deep neural networks come at the cost of computational\ncomplexity that limits their practicality for deployment on portable devices.\nWe propose the low-rank transformer (LRT), a memory-efficient and fast neural\narchitecture that significantly reduces the parameters and boosts the speed of\ntraining and inference for end-to-end speech recognition. Our approach reduces\nthe number of parameters of the network by more than 50% and speeds up the\ninference time by around 1.35x compared to the baseline transformer model. The\nexperiments show that our LRT model generalizes better and yields lower error\nrates on both validation and test sets compared to an uncompressed transformer\nmodel. The LRT model outperforms those from existing works on several datasets\nin an end-to-end setting without using an external language model or acoustic\ndata.\n

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.847
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.076
GPT teacher head0.196
Teacher spread0.120 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2019
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicSpeech Recognition and SynthesisFrench-language works237,207