The remarkable emergence of large language models (LLM) and their vast capabilities have opened a possibility for applications in various fields, including speech emotion recognition (SER). Despite the advancement of SER methods and the abundance of speech data, the requirement of having speech data labeled with emotions is a challenge to fulfill, considering the cost of human annotation. In this study, we propose utilizing LLM to annotate emotional speeches, investigating the use of conversation sequence transcription, and incorporating the textual acoustic feature descriptors into the prompt. Furthermore, we also examine the application of annotation results on emotional speeches as training and augmentation data. Our experiment using the IEMOCAP dataset shows that emotional speech annotation using LLMs can outperform human annotation with possibly lower annotation costs. The SER trained using the annotation result as a whole training data or augmentation data reaches a performance close to state-of-the-art SER methods.

Conventional automatic speech recognition systems do not produce punctuation marks which are important for the readability of the speech recognition results.They are also needed for subsequent natural language processing tasks such as machine translation.There have been a lot of works on punctuation prediction models that insert punctuation marks into speech recognition results as post-processing.However, these studies do not utilize acoustic information for punctuation prediction and are directly affected by speech recognition errors.In this study, we propose an end-to-end model that takes speech as input and outputs punctuated texts.This model is expected to predict punctuation robustly against speech recognition errors while using acoustic information.We also propose to incorporate an auxiliary loss to train the model using the output of the intermediate layer and unpunctuated texts.Through experiments, we compare the performance of the proposed model to that of a cascaded system.The proposed model achieves higher punctuation prediction accuracy than the cascaded system without sacrificing the speech recognition error rate.It is also demonstrated that the multi-task learning using the intermediate output against the unpunctuated text is effective.Moreover, the proposed model has only about 1/7th of the parameters compared to the cascaded system.

We present a novel representation for point clouds that encapsulates the local characteristics of the underlying structure. The key idea is to embed an implicit representation of the point cloud, namely the distance field, into neural networks. One neural network is used to embed a portion of the distance field around a point. The resulting network weights are concatenated to be used as a representation of the corresponding point cloud instance. To enable comparison among the weights, Extreme Learning Machine (ELM) is employed as the embedding network. Invariance to scale and coordinate change can be achieved by introducing a scale commutative activation layer to the ELM, and aligning the distance field into a canonical pose. Experimental results using our representation demonstrate that our proposal is capable of similar or better classification and segmentation performance compared to the state-of-the-art point-based methods, while requiring less time for training.

Our research aim is the automatic generation of a researcher's research history from research articles published on the internet. Research history generation based on the k-Means clustering algorithm has been proposed in previous work. However, the performance of the k-Means algorithm is unsatisfactory. We propose a method based on Maximum Margin Clustering (MMC). MMC is a new clustering algorithm based on Support Vector Machines (SVM). It is known that MMC is better than existing clustering algorithms such as k-Means. In this paper, we describe how to convert articles into vectors using metainformation about them and how to decide an initial setting for MMC automatically. We demonstrate by experiment that the purity of a method based on MMC is about 0.58 and its entropy is about 0.415. This result is better than that achieved in previous work (purity: 0.35, entropy: 0.47).

In Japanese constructions of the form [N1 no Adj N2], the adjective Adj modifies either N1 or N2. Determing the semantic dependencies of adjective in such phrase is an important task for machine translation. This paper describes a method for determining the adjective dependency in such constructions using decision lists, and inducing decision lists from training contexts with correct semantic dependencies and without. Based on evaluation, our method is able to determine adjective dependency with an precision of about 94%. We further analyze rules in the induced decision lists and examine effective features to determine the semantic dependencies of adjectives.