A physiological articulatory model has been constructed using a fast computation method, which replicates midsagittal regions of the speech organs to simulate articulatory movements during speech. This study aims to improve the accuracy of modeling by using the displacement-based finite-element method and to develop a new approach for controlling the model. A “semicontinuum” tongue tissue model was realized by a discrete truss structure with continuum viscoelastic cylinders. Contractile effects of the muscles were systemically examined based on model simulations. The results indicated that each muscle drives the tongue toward an equilibrium position (EP) corresponding to the magnitude of the activation forces. The EPs shifted monotonically as the activation force increased. The monotonic shift revealed a unique and invariant mapping, referred to as an EP map, between a spatial position of the articulators and the muscle forces. This study proposes a control method for the articulatory model based on the EP maps, in which co-contractions of agonist and antagonist muscles are taken into account. By utilizing the co-contraction, the tongue tip and tongue dorsum can be controlled to reach their targets independently. Model simulation showed that the co-contraction of agonist and antagonist muscles could increase the stability of a system in dynamic control.

Emotion information from speech can effectively help robots understand speaker’s intentions in natural human-robot interaction. The human auditory system can easily track temporal dynamics of emotion by perceiving the intensity and fundamental frequency of speech, and focus on the salient emotion regions. Therefore, speech emotion recognition combined with the auditory mechanism and attention mechanism may be an effective way. Some previous studies used auditory-based static features to identify emotion while ignoring the emotion dynamics. Some other studies used attention models to capture the salient regions of emotion while ignoring cognitive continuity. To fully utilize the auditory and attention mechanism, we first investigate temporal modulation cues from auditory front-ends and then propose a joint deep learning model that combines 3D convolutions and attention-based sliding recurrent neural networks (ASRNNs) for emotion recognition. Our experiments on the IEMOCAP and MSP-IMPROV datasets indicate that the proposed method can be effectively used to recognize the emotions of speech from temporal modulation cues. The subjective evaluation shows that the attention patterns of the attention model are basically consistent with human behaviors in recognizing the emotions.

Spiking neural networks (SNNs) are considered as a potential candidate to overcome current challenges, such as the high-power consumption encountered by artificial neural networks (ANNs); however, there is still a gap between them with respect to the recognition accuracy on various tasks. A conversion strategy was, thus, introduced recently to bridge this gap by mapping a trained ANN to an SNN. However, it is still unclear that to what extent this obtained SNN can benefit both the accuracy advantage from ANN and high efficiency from the spike-based paradigm of computation. In this article, we propose two new conversion methods, namely TerMapping and AugMapping. The TerMapping is a straightforward extension of a typical threshold-balancing method with a double-threshold scheme, while the AugMapping additionally incorporates a new scheme of augmented spike that employs a spike coefficient to carry the number of typical all-or-nothing spikes occurring at a time step. We examine the performance of our methods based on the MNIST, Fashion-MNIST, and CIFAR10 data sets. The results show that the proposed double-threshold scheme can effectively improve the accuracies of the converted SNNs. More importantly, the proposed AugMapping is more advantageous for constructing accurate, fast, and efficient deep SNNs compared with other state-of-the-art approaches. Our study, therefore, provides new approaches for further integration of advanced techniques in ANNs to improve the performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic computing.

Multimodal Sentiment Analysis (MSA) stands as a critical research frontier, seeking to comprehensively unravel human emotions by amalgamating text, audio, and visual data. Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge, particularly when emotional polarities across various segments appear similar. In this paper, our objective is to spotlight emotion-relevant attributes of audio and visual modalities to facilitate multimodal fusion in the context of nuanced emotional shifts in visual-audio scenarios. To this end, we introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions aimed at accentuating emotional features of visual-audio content. DEVA employs an Emotional Description Generator (EDG) to transmute raw audio and visual data into textualized sentiment descriptions, thereby amplifying their emotional characteristics. These descriptions are then integrated with the source data to yield richer, enhanced features. Furthermore, DEVA incorporates the Text-guided Progressive Fusion Module (TPF), leveraging varying levels of text as a core modality guide. This module progressively fuses visual-audio minor modalities to alleviate disparities between text and visual-audio modalities. Experimental results on widely used sentiment analysis benchmark datasets, including MOSI, MOSEI, and CH-SIMS, underscore significant enhancements compared to state-of-the-art models. Moreover, fine-grained emotion experiments corroborate the robust sensitivity of DEVA to subtle emotional variations.

Neural text-to-speech (TTS) has achieved humanlike synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. TTS systems are typically built using a single speaker's voice, but there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper combines text-based and speech-based self-supervised learning models for multilingual speech synthesis. Our proposed model has zero-shot generalization ability not only for unseen speakers but also for unseen languages. We have conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetically lowresource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.