• Digital Humanities and Cultural Heritage
• CN close
• IEEE/ACM Transactions on Audio Spee... close

Personalizing a music emotion recognition model is needed because the perception of music emotion is highly subjective, but it is a time-consuming process. In this paper, we consider how to expedite the personalization process that begins with a general model trained offline using a general user base and progressively adapts the model to a music listener using the emotion annotations of the listener. Specifically, we focus on reducing the number of user annotations needed for the personalization. We investigate and evaluate four component tying methods: single group tying, quadrantwise tying, hierarchical tying, and random tying. These methods aim to exploit the available annotations by identifying related model parameters on-the-fly and updating them jointly. In the evaluation, we use the AMG1608 dataset, which contains the clip-level valence-arousal emotion ratings of 1608 30-s music clips annotated by 665 listeners. Also, we use the acoustic emotion Gaussians model as the general model that uses a mixture of Gaussian components to learn the mapping between the acoustic feature space and the emotion space. The results show that the model adaptation with component tying requires only 10-20 personal annotations to obtain the same level of prediction accuracy as the baseline model adaptation method that uses 50 personal annotations without component tying.

Sentence similarity modeling lies at the core of many natural language processing applications, and thus has received much attention. Owing to the success of word embeddings, recently, popular neural network methods achieved sentence embedding. Most of them focused on learning semantic information and modeling it as a continuous vector, yet the syntactic information of sentences has not been fully exploited. On the other hand, prior works have shown the benefits of structured trees that include syntactic information, while few methods in this branch utilized the advantages of word embeddings and another powerful technique—attention weight mechanism. This paper suggests to absorb their advantages by merging these techniques in a unified structure, dubbed as attention constituency vector tree (ACVT). Meanwhile, this paper develops a new tree kernel, known as ACVT kernel, which is tailored for sentence similarity measure based on the proposed structure. The experimental results, based on 19 widely used semantic textual similarity datasets, demonstrate that our model is effective and competitive, when compared against state-of-the-art models. Additionally, the experimental results validate that many attention weight mechanisms and word embedding techniques can be seamlessly integrated into our model, demonstrating the robustness and universality of our model.

Recent researches try to integrate word information into the character-based Chinese NER by modifying the structure of the standard BiLSTM-CRF model. They follow the paradigm of explicitly modeling forward and backward sequences, adopting an LSTM variant that takes both characters and words as input for each direction. Though enriching the representations, these models cannot fully exploit the interaction between future and past contexts. In this paper, we propose a novel word-character graph convolution network (WC-GCN) which uses a cross GCN block to simultaneously process the word-character directed acyclic graphs (DAGs) of two directions. To improve the capture of long-distance dependency, a global attention GCN block is introduced to learn node representations conditioned on a global context. In both blocks, unlike previous works where each word is attached to its associated character or taken as a shortcut between LSTM cells, words and characters are treated equally as nodes in the graph and have their instance-specific representations. Experiments on four widely used datasets show that our proposed model can work standalone or with the standard BiLSTM. Both forms can outperform previous LSTM-based models without training on extra corpora while only an external lexicon and its corresponding pretrained character and word embeddings are needed.

Natural language understanding (NLU) converts sentences into structured semantic forms. The paucity of annotated training samples is still a fundamental challenge of NLU. To solve this data sparsity problem, previous work based on semi-supervised learning mainly focuses on exploiting unlabeled sentences. In this work, we introduce a dual task of NLU, semantic-to-sentence generation (SSG), and propose a new framework for semi-supervised NLU with the corresponding dual model. The framework is composed of dual pseudo-labeling and dual learning method, which enables an NLU model to make full use of data (labeled and unlabeled) through a closed-loop of the primal and dual tasks. By incorporating the dual task, the framework can exploit pure semantic forms as well as unlabeled sentences, and further improve the NLU and SSG models iteratively in the closed-loop. The proposed approaches are evaluated on two public datasets (ATIS and SNIPS). Experiments in the semi-supervised setting show that our methods can outperform various baselines significantly, and extensive ablation studies are conducted to verify the effectiveness of our framework. Finally, our method can also achieve the state-of-the-art performance on the two datasets in the supervised setting. Our code is available at \url{https://github.com/rhythmcao/slu-dual-learning.git}. Comment: 12 pages, 4 figures; Accepted for IEEE/ACM Transactions on Audio Speech and Language Processing

The popular n-gram language model (LM) is weak for unfrequent words. Conventional approaches such as class-based LMs pre-define some sharing structures (e.g., word classes) to solve the problem. However, defining such structures requires prior knowledge, and the context sharing based on these structures is generally inaccurate. This paper presents a novel similar word model to enhance unfrequent words. In principle, we enrich the context of an unfrequent word by borrowing context information from some “similar words.” Compared to conventional class-based methods, this new approach offers a fine-grained context sharing by referring to words that best match the target word, and it is more flexible as no sharing structures need to be defined by hand. Experiments on a large-scale Chinese speech recognition task demonstrated that the similar word approach can improve performance on unfrequent words significantly, while keeping the performance on general tasks almost unchanged.

Prior studies show that cross-lingual semantic role labeling (SRL) can be achieved by model transfer under the help of universal features. In this paper, we fill the gap of cross-lingual SRL by proposing an end-to-end SRL model that incorporates a variety of universal features and transfer methods. We study both the bilingual transfer and multi-source transfer, under gold or machine-generated syntactic inputs, pre-trained high-order abstract features, and contextualized multilingual word representations. Experimental results on the Universal Proposition Bank corpus indicate that performances of the cross-lingual SRL can vary by leveraging different cross-lingual features. In addition, whether the features are gold-standard also has an impact on performances. Precisely, we find that gold syntax features are much more crucial for cross-lingual SRL, compared with the automatically-generated ones. Moreover, universal dependency structure features are able to give the best help, and both pre-trained high-order features and contextualized word representations can further bring significant improvements. Comment: Accepted at TASLP

In machine translation evaluation, the traditional wisdom measures model's generalization ability in an average sense, for example by using corpus BLEU. However, the statistics of corpus BLEU cannot provide comprehensive understanding and fine-grained analysis on model's generalization ability. As a remedy, this paper attempts to understand NMT at fine-grained level, by detecting contextual barriers within an unseen input sentence that cause the degradation in model's translation quality. It proposes a principled definition of source contextual barriers as well as its modified version which is tractable in computation and operates at word-level. Based on the modified one, three simple methods are proposed for barrier detection by search-aware risk estimation through counterfactual generation. Extensive analyses are conducted on those detected contextual barrier words on both Zh $\Leftrightarrow$ En NIST benchmarks. Potential usages motivated from barrier words are also discussed.

Expressive text-to-speech (E-TTS) synthesis is important for enhancing user experience in communication with machines using the speech modality. However, one of the challenges in E-TTS is the lack of a precise description of emotions. Previous categorical specifications may be insufficient for describing complex emotions. The dimensional specifications face the difficulty of ambiguity in annotation. This work advocates a new approach of describing emotive speech acoustics using spoken exemplars. We investigate methods to extract emotion descriptions from the input exemplar of emotive speech. The measures are combined to form two descriptors, based on capsule network (CapNet) and residual error network (RENet). The first is designed to consider the spatial information in the input exemplary spectrogram, and the latter is to capture the contrastive information between emotive acoustic expressions. Two different approaches are applied for conversion from the variable-length feature sequence to fixed-size description vector: (1) dynamic routing groups similar capsules to the output description; and (2) recurrent neural network's hidden states store the temporal information for the description. The two descriptors are integrated to a state-of-the-art sequence-to-sequence architecture to obtain an end-to-end architecture that is optimized as a whole towards the same goal of generating correct emotive speech. Experimental results on a public audiobook dataset demonstrate that the two exemplar-based approaches achieve significant performance improvement over the baseline system in both emotion similarity and speech quality.

Recently, many efforts have been devoted to generating responses expressing a specific emotion or relating to a given topic in a controlled manner. However, limited attention has been given to generating responses with a specified syntactic pattern, which makes it possible to imitate someone’s way of speaking in dialogue. To fulfill this goal, we propose two models to generate syntax-aware responses: a gross-constraint and a specific-constraint model. The former controls the syntactic patterns of generated responses at sentence-level, while the latter works at smaller language units, such as words or phrases, being capable of manipulating the syntactic structures of responses in a more subtle manner. The extensive experimental results on two different datasets show that both the two models not only can generate meaningful responses with a specific and coherent structure but also improve on the diversity of generated responses, with similar gains in readability, relevance, and diversity as measured by human judges.