Formant estimation from vowel segments, is very useful for linguistic purposes. Traditionally, formants are estimated using classical signal processing methods and statistical models. The averaged continuous extraction of formant frequency along the vowel segments is taken as the formant of vowels. New approaches using neural networks to predict vowel formants on an annotated database, where the input is the acoustic features and output is the mean formant frequency value. Recently, the Bilinear Network (BL) and Temporal Attention-Augmented Bilinear Network (TABL) have proven to be very effective on financial time-series analysis task, compared to recurrent networks and convolution networks. Similar to our work, we explored how to extend the structure of BL and learn from TABL to produce better short-term modeling capability for vowel formant estimation. More specifically, we proposed to replace the attention mechanism with sigmoid gate and use a learnable parameter to dynamically integrate the first linear transformation output, thus learning better representation of BL. Experiments on the vowels test set of public VTR corpus showed that our approach significantly surpassed DNN, CNN, BL and achieved slightly better performance than the poweful TABL model in terms of mean absolute error and mean absolute percent error rate on F1, F2, F3 and overall.

Implicit discourse relation recognition (IDRR) still faces challenges in achieving high accuracy compared to explicit discourse relation recognition. Many existing approaches attempt to combine explicit and implicit data. However, language differences and variations in category distribution make it challenging to use multitask learning to directly optimize IDRR task. This paper considers explicit data as out-of-domain data and implicit data as in-domain data, proposed a shared-private-based framework with dynamic dependency matching (SPDDM) for IDRR task. This framework explores the deep-level syntactic correlation between explicit and implicit data by encoding dependency grammar information through cross-attention mechanism and confuse it to shared-private framework through dynamic matching . Extensive experiments on the popular PDTB datasets show that our model achieves state-of-the-art performance, and a detailed analysis highlights the efficiency of our proposed framework.

This paper proposes incorporating linguistic semantic information into discourse relation recognition and constructing a Semantic Augmented Chinese Discourse Corpus (SACA) comprising 9546 adversative complex sentences. In adversative complex sentences, we suggest a quadruple (P, Q, R, $Q_{\beta }$) representing internal semantic elements, where the semantic opposition between Q and $Q_{\beta }$ forms the basis of the adversative relationship. P denotes the premise, and R represents the adversative reason. The overall annotation approach of this corpus follows the Penn Discourse Treebank (PDTB), except for the classification of senses. We combined insights from the Chinese Discourse Treebank (CDTB) and obtained eight sense categories for Chinese adversative complex sentences. Based on this corpus, we explore the relationship between sense classification and internal semantic elements within our newly proposed Chinese Adversative Discourse Relation Recognition (CADRR) task. Leveraging deep learning techniques, we constructed various classification models and the model that utilizes internal semantic element features, demonstrating their effectiveness and the applicability of our SACA corpus. Compared with pre-trained models, our model incorporates internal semantic element information to achieve state-of-the-art performance.