MétaCan
Menu
Back to cohort

Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis

2022· article· en· W4297841867 on OpenAlex
Julian Zaïdi, Hugo Seuté, Benjamin van Niekerk, Marc-André Carbonneau

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInterspeech 2022 · 2022
Typearticle
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsUbisoft (Canada)
Fundersnot available
KeywordsProsodyComputer scienceSpeech synthesisSpeech recognitionTransfer (computing)Natural language processing

Abstract

fetched live from OpenAlex

This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text.This is one of the most challenging, and rarely directly addressed, task in speech synthesis, especially for highly expressive data.Daft-Exprt uses FiLM conditioning layers to strategically inject different prosodic information in all parts of the architecture.The model explicitly encodes traditional low-level prosody features such as pitch, loudness and duration, but also higher level prosodic information that helps generating convincing voices in highly expressive styles.Speaker identity and prosodic information are disentangled through an adversarial training strategy that enables accurate prosody transfer across speakers.Experimental results show that Daft-Exprt significantly outperforms strong baselines on inter-text crossspeaker prosody transfer tasks, while yielding naturalness comparable to state-of-the-art expressive models.Moreover, results indicate that the model discards speaker identity information from the prosody representation, and consistently generate speech with the desired voice.We publicly release our code 1 and provide speech samples from our experiments 2 .

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.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.777
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0020.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0060.000

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 head0.025
GPT teacher head0.281
Teacher spread0.256 · 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