Book Review

Chen, Wentao; Liu, Kanglong

doi:10.1016/j.acorp.2023.100045

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first divided the sentences into the aforementioned 29 words and phrases consisting of 1 to 4 Chinese characters. We trained this model on a collection of sentences from the CCL corpus 47 that included transferring pairs (transfers) between those words from the 29-word set. After that, we used a Viterbi decoder to determine the most likely sequence of words given the predicted tonal syllable probabilities from the tone decoder and syllable decoder, as well as the word-sequence probabilities from the natural language model 8 .…”

Section: Methodsmentioning

confidence: 99%

“…We used CCL corpus from Peking University 47 to distill training dataset for our domain-specific language model. We first measure the number of transfers between each two phrases (the counts of the previous phrase transferred to the first word of the next phrase in the whole CCL corpus).…”

Section: Methodsmentioning

confidence: 99%

“…To train a domain-specific language model for the sentence task, we used CCL corpus from Peking University 47 . We first measure the number of transfers between each two phrases (the counts of the previous phrase transferred to the first word of the next phrase in the whole CCL corpus).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A brain-to-text framework of decoding natural tonal sentences

Zhang,

Wang,

Qian

et al. 2024

Preprint

View full text Add to dashboard Cite

Speech brain-computer interfaces (BCIs) directly translate brain activity into speech sound and text, yet decoding tonal languages like Mandarin Chinese poses a significant, unexplored challenge. Despite successful cases in non-tonal languages, the complexities of Mandarin, with its distinct syllabic structures and pivotal lexical information conveyed through tonal nuances, present challenges in BCI decoding. Here we designed a brain-to-text framework to decode Mandarin tonal sentences from invasive neural recordings. Our modular approach dissects speech onset, base syllables, and lexical tones, integrating them with contextual information through Bayesian likelihood and the Viterbi decoder. The results demonstrate accurate tone and syllable decoding under variances in continuous naturalistic speech production, surpassing previous intracranial Mandarin tonal syllable decoders in decoding accuracy. We also verified the robustness of our decoding framework and showed that the model hyperparameters can be generalized across participants of varied gender, age, education backgrounds, pronunciation behaviors, and coverage of electrodes. Our pilot study shed lights on the feasibility of more generalizable brain-to-text decoding of natural tonal sentences from patients with high heterogeneities.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%