MétaCan
Menu
Back to cohort

High-Frequency Component Restoration for Kalman Filter Based Speech Enhancement

2020· article· en· W3089869259 on OpenAlexaff
Hongjiang Yu, Wei‐Ping Zhu, Benoı̂t Champagne

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSpeech and Audio Processing
Canadian institutionsMcGill UniversityConcordia University
Fundersnot available
KeywordsSpeech enhancementKalman filterIntelligibility (philosophy)Computer scienceSpeech recognitionComponent (thermodynamics)Distortion (music)Artificial intelligenceNoise reductionBandwidth (computing)Telecommunications

Abstract

fetched live from OpenAlex

In this paper, we present a deep neural network (DNN) based algorithm to restore the high-frequency (HF) component of the enhanced speech processed by Kalman filtering, where the DNN is applied for estimating the magnitude of HF component from the low-frequency (LF) counterpart. The complete HF component is then computed with the estimated magnitude given by the DNN and the phase of the Kalman filtered speech. By incorporating our restoration algorithm into Kalman filter based speech enhancement method, our new speech enhancement system is able to recover the HF component with better perceptual quality and less distortion. Experimental results demonstrate that the proposed method outperforms the state-of-the-art Kalman filter based method in terms of both speech quality and intelligibility.

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 categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.400
Threshold uncertainty score0.377

Codex and Gemma teacher scores by category

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

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 head0.035
GPT teacher head0.258
Teacher spread0.223 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

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

Citations3
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicSpeech and Audio ProcessingFrench-language works237,207