MétaCan
Menu
Back to cohort
Record W4253290035 · doi:10.1121/2.0000395

Towards real-time two-dimensional wave propagation for articulatory speech synthesis

2016· article· en· W4253290035 on OpenAlexaff
Victor Zappi, Arvind Vasuvedan, Andrew J. Allen, Nikunj Raghuvanshi, Sidney Fels

Bibliographic record

VenueProceedings of meetings on acoustics · 2016
Typearticle
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsUniversity of British Columbia
FundersNvidia
KeywordsComputer scienceFormantSolverDiscretizationSpeech recognitionSpeech enhancementAcousticsArtificial intelligence

Abstract

fetched live from OpenAlex

The precise simulation of voice production is a challenging task, often characterized by a tradeoff between quality and speed. The usage of 3D acoustic models of realistic vocal tracts produces extremely precise results, at the cost of running simulations that may take several minutes to synthesize a few milliseconds of audio. In contrast, 1D articulatory vocal synthesizers rely on highly simplified acoustic and anatomical models to achieve real-time performances, but can only partially match the spectra of realistic vocal tracts. In this work, we present a novel articulatory vocal synthesizer, based on a fast 2D propagation model running on a graphics card (GPU). The system can run in real-time under specific conditions and, differently from 1D synthesizers, allows for simulating airflow propagation through asymmetric and curved geometries. This paper covers details on the GPU implementation of the different components of the system, including the 2D Finite-Difference Time-Domain wave solver and the excitation mechanism. A preliminary evaluation is presented, using area functions to simulate static vowels. Three different resolutions are tested, combined with two alternative ways of discretizing the 2D geometries. The computed formants are overall characterized by small positional errors while computational times are comparable with those from 1D systems.

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)0.001
metaresearch head score (Gemma)0.003
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: Empirical · Consensus signal: Empirical
Teacher disagreement score0.292
Threshold uncertainty score0.693

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.003
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 head0.020
GPT teacher head0.242
Teacher spread0.222 · 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
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

Citations6
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of meetings on acousticsSame topicSpeech Recognition and SynthesisFrench-language works237,207