CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Makarov, Peter; Clematide, Simon

doi:10.18653/v1/2020.sigmorphon-1.19

Cited by 7 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CLUZH team adapted their earlier model, character-level neural transducer, to work on large datasets (Makarov and Clematide, 2020). The model has previously shown superior performance, especially in low-resource scenarios.…”

Section: Baseline Systemsmentioning

confidence: 99%

“…As a basis for all our submissions, we use a neural character-level transducer that edits the input string into the output string by a sequence of traditional edit actions: substitutions, insertions, deletion, and copy. The specific version of this approach was developed for grapheme-to-phoneme conversion (Makarov and Clematide, 2020a). Such neural transducers have typically performed well in morphological and related character-level transduction tasks in low to medium training data settings.…”

Section: Model Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

2022

View full text Add to dashboard Cite

Speech consists of a continuously-varying acoustic signal. Yet human listeners experience it as sequences of discrete speech sounds, which are used to recognise words. To examine how the human brain appropriately sequences the speech signal, we recorded two-hour magnetoencephalograms from 21 subjects listening to short narratives. Our analyses show that the brain continuously encodes the three most recently heard speech sounds in parallel, and maintains this information long past the sensory input. Each speech sound has a representation that evolves over time, jointly encoding both its phonetic features and time elapsed since onset. This allows the brain to represent the relative order and phonetic content of the phonetic sequence. These dynamic representations are active earlier when phonemes are more predictable, and are sustained longer when lexical identity is uncertain. The flexibility in the dynamics of these representations paves the way for further understanding of how such sequences may be used to interface with higher order structure such as morphemes and words.Bio: Laura Gwilliams received her PhD in Psychology with a focus in Cognitive Neuroscience from New York University in May 2020. Currently she is a post-doctoral researcher at UCSF, using MEG and ECoG data to understand how linguistic structures are parsed and composed while listening to continuous speech. The ultimate goal of Laura's research is to describe speech comprehension in terms of what operations are applied to the acoustic signal; which representational formats are generated and manipulated (e.g. phonetic, syllabic, morphological), and under what processing architecture.

show abstract

Section: Baseline Systemsmentioning

confidence: 99%

Section: Model Descriptionmentioning

confidence: 99%

Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

2022

View full text Add to dashboard Cite

show abstract

“…During training, an aggressive exploration schedule p sampling (i) = 1 1+exp(i) where i is the training epoch number, exposes the model to configurations sampled by executing edit actions from the model. For an extended description of the SED policy and IL training, we refer the reader to the last year's system description paper (Makarov and Clematide, 2020).…”

Section: Model Descriptionmentioning

confidence: 99%

CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline

Clematide¹,

Makarov²

2021

Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

Self Cite

View full text Add to dashboard Cite

This paper describes the submission by the team from the Department of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task 1 of the SIGMORPHON 2021 challenge in the low and medium settings. The submission is a variation of our 2020 G2P system, which serves as the baseline for this year's challenge. The system is a neural transducer that operates over explicit edit actions and is trained with imitation learning. For this challenge, we experimented with the following changes: a) emitting phoneme segments instead of single character phonemes, b) input character dropout, c) a mogrifier LSTM decoder (Melis et al., 2019), d) enriching the decoder input with the currently attended input character, e) parallel BiLSTM encoders, and f) an adaptive batch size scheduler. In the low setting, our best ensemble improved over the baseline, however, in the medium setting, the baseline was stronger on average, although for certain languages improvements could be observed.

show abstract

“…Two forms of error analysis were employed here. First, after Makarov and Clematide (2020), the most frequent error types in each language are shown in Table 7. From this table it is clear that many errors can be attributed either to the ambiguity of a language's writing system.…”

Section: Error Analysismentioning

confidence: 99%

Results of the Second SIGMORPHON Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Ashby¹,

Bartley²,

Clematide³

et al. 2021

Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

Self Cite

View full text Add to dashboard Cite

Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task. The second iteration of the SIGMORPHON shared task on multilingual grapheme-to-phoneme conversion features many improvements from the previous year's task (Gorman et al. 2020), including additional languages, a stronger baseline, three subtasks varying the amount of available resources, extensive quality assurance procedures, and automated error analyses. Four teams submitted a total of thirteen systems, at best achieving relative reductions of word error rate of 11% in the high-resource subtask and 4% in the low-resource subtask.

show abstract

CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Cited by 7 publications

References 11 publications

Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline

Results of the Second SIGMORPHON Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Contact Info

Product

Resources

About