MétaCan
Menu
Back to cohort

Automatic Speech Segmentation in French / Segmentação automática da fala em francês

2018· article· en· W2897517493 on OpenAlexaff
Philippe Martin

Bibliographic record

VenueRevista de Estudos da Linguagem · 2018
Typearticle
Languageen
FieldPsychology
TopicPhonetics and Phonology Research
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsLinguisticsSyllableStress (linguistics)Stress (linguistics)AdverbPhraseLexiconComputer scienceNounSpeech recognitionArtificial intelligencePhilosophy

Abstract

fetched live from OpenAlex

Abstract: Whether we read aloud or silently, we segment speech not in words, but in accent phrases, i.e. sequences containing only one stressed syllable (excluding emphatic stress). In lexically stressed languages such as Italian or English, the location of stress in a noun, an adverb, a verb or an adjective (content words) is defined in the lexicon, and accent phrases include one single content word together with its associated grammatical words. In French, a language deprived from lexical stress, accent phrases are defined by the time it takes to read or pronounce them. Therefore, actual phrasing, i.e. the segmentation into accent phrases, depends strongly on the speech rate chosen by the speaker or the reader, whether in oral or silent reading mode. With a slow speech rate, all content words form accent phrases whose final syllables are stressed, whereas a fast speech rate could merge up to 10 or 11 syllables together in a single accent phrase with more than one content word. Based on this observation, and on other properties of stressed syllables, a computer algorithm for automatic phrasing, operating in a top-down fashion, is presented and applied to two examples of read and spontaneous speech.Keywords: accent phrase; French; phrasing; stress location; boundary detection.Resumo: Quando lemos em voz alta ou silenciosamente, segmentamos a fala em palavras, mas em grupos acentuais, i.e., sequências contendo uma única sílaba acentuada (excluindo-se acento enfático). Em línguas lexicalmente acentuadas como o italiano ou o inglês, a localização do acento em um substantivo, um advérbio, um verbo ou em um adjetivo (palavras lexicais) é definida no léxico, e sintagmas acentuais incluem uma única palavra lexical, acompanhada das palavras gramaticais a ela associadas. Em francês, uma língua que não possui acento lexical, sintagmas acentuais são definidos pelo tempo que se leva para lê-los ou pronunciá-los. Assim, os constituintes concretos, i.e., a segmentação em grupos acentuais, depende fortemente da velocidade de fala escolhida pelo falante ou leitor, tanto na fala como na leitura silenciosa. Com uma velocidade de fala baixa, todas as palavras lexicais formam grupos acentuais cujas sílabas finais são acentuadas, enquanto o ritmo de fala rápido poderia juntar de 10 a 11 sílabas em um mesmo grupo acentual contendo mais de uma palavra lexical. Com base nessa observação e em outras propriedades das sílabas acentuadas, um algoritmo computacional para segmentação automática, atuando de maneira top-down é apresentado e aplicado a dois exemplos de leitura e fala espontânea.Palavras-chave: grupo acentual; francês; segmentação; posição do acento; detecção de fronteira.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.678
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 studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0050.002

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 head0.032
GPT teacher head0.372
Teacher spread0.340 · 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; both teacher heads agree on what is shown here.

Study designObservational
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

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueRevista de Estudos da LinguagemSame topicPhonetics and Phonology ResearchFrench-language works237,207