By using deep learning approaches, Speech Emotion Recog-nition (SER) on a single domain has achieved many excellentresults. However, cross-domain SER is still a challenging taskdue to the distribution shift between source and target domains.In this work, we propose a Domain Adversarial Neural Net-work (DANN) based approach to mitigate this distribution shiftproblem for cross-lingual SER. Specifically, we add a languageclassifier and gradient reversal layer after the feature extractor toforce the learned representation both language-independent andemotion-meaningful. Our method is unsupervised, i. e., labelson target language are not required, which makes it easier to ap-ply our method to other languages. Experimental results showthe proposed method provides an average absolute improve-ment of 3.91% over the baseline system for arousal and valenceclassification task. Furthermore, we find that batch normaliza-tion is beneficial to the performance gain of DANN. Thereforewe also explore the effect of different ways of data combinationfor batch normalization.
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this work, we propose mSimCSE, which extends SimCSE to multilingual settings and reveal that contrastive learning on English data can surprisingly learn high-quality universal cross-lingual sentence embeddings without any parallel data. In unsupervised and weakly supervised settings, mSimCSE significantly improves previous sentence embedding methods on cross-lingual…
Peking University（北京大学）；The University of Sydney（悉尼大学）；iFlytek Research（讯飞研究院）
Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on sophisticated translation models. In this study, we propose a super lightweight unsupervised word alignment model named MirrorAlign, in which bidirectional symmetric attention trained with a contrastive learning objective is introduced, and an agreement loss is employed to bind the attention maps, such that the alignments follow mirror-like symmetry hypothesi…
Beihang University（北京航空航天大学）；National Computer Network Emergency Response Technical Team / Coordination Center of China（国家计算机网络应急技术处理协调中心）
For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means. Typically, these approaches adopt a teacher-student architecture, where the teacher network is trained in the source language, and the student network seeks to learn knowledge from the teacher network and is expected to perform well in the target language. Despite the impressive performance achieved by these methods, we argue that they have two limitations. Fir…
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Lazada, Alibaba Group（阿里巴巴集团Lazada）
Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. Meanwhile, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNNbased methods, we successfully transform the cross-lingual EA problem into the assignment problem. Based on this finding, we propose a frustratingly Simple but Effective …
In real-world applications such as emotion recognition from recorded brain activity, data are captured from electrodes over time. These signals constitute a multidimensional time series. In this paper, Echo State Network (ESN), a recurrent neural network with a great success in time series prediction and classification, is optimized with different neural plasticity rules for classification of emotions based on electroencephalogram (EEG) time series. Actually, the neural plasticity rules are a kind of unsupervised learning adapted for the reservoir, i.e. the hidden layer of ESN. More specifical…
Meta AI Research（Meta人工智能研究院）；Ecole normale supérieure, PSL University（巴黎文理研究大学高等师范学院）；Inria（法国国家信息与自动化研究所）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；University College London（伦敦大学学院）
Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and tasks where large training sets are available. However, they do not transfer well to new applications with no training data, and are outperformed by unsupervised term-frequency methods such as BM25. In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various…
HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding
University of Science and Technology Beijing（北京科技大学）；Agency for Science, Technology and Research（新加坡科技研究局）；Nanyang Technological University（南洋理工大学）；University of Technology Sydney（悉尼科技大学）
IBM Research AI（IBM研究人工智能部门）；Kitchawan Road, Yorktown Heights, NY 10598, USA（美国纽约州约克镇高地基奇瓦诺路1101号（IBM相关地址，按要求忽略地址细节，仅保留机构级别信息，但此处原文中该地址与前一affiliation同属一个机构，因此提取核心机构））
Relation extraction (RE) is one of the most important tasks in information extraction, as it provides essential information for many NLP applications. In this paper, we propose a cross-lingual RE approach that does not require any human annotation in a target language or any cross-lingual resources. Building upon unsupervised cross-lingual representation learning frameworks, we develop several deep Transformer based RE models with a novel encoding scheme that can effectively encode both entity location and entity type information. Our RE models, when trained with English data, outperform sever…
Speech Emotion Recognition (SER) in a single language has achieved remarkable results through deep learning approaches in the last decade. However, cross-lingual SER remains a challenge in real-world applications due to a great difference between the source and target domain distributions. To address this issue, we propose an unsupervised cross-lingual Neural Network with Pseudo Multilabel (NNPM) that is trained to learn the emotion similarities between source domain features inside an external memory adjusted to identify emotion in cross-lingual databases. NNPM introduces a novel approach tha…
The Experimental High School Attached to Beijing Normal University（北京师范大学附属实验中学）
A speech emotion recognition algorithm based on multi-feature and Multi-lingual fusion is proposed in order to resolve low recognition accuracy caused by lack of large speech dataset and low robustness of acoustic features in the recognition of speech emotion. First, handcrafted and deep automatic features are extracted from existing data in Chinese and English speech emotions. Then, the various features are fused respectively. Finally, the fused features of different languages are fused again and trained in a classification model. Distinguishing the fused features with the unfused ones, the r…
Department of Computer Science, Columbia University（哥伦比亚大学计算机科学系）
The majority of existing speech emotion recognition models are trained and evaluated on a single corpus and a single language setting. These systems do not perform as well when applied in a cross-corpus and cross-language scenario. This paper presents results for speech emotion recognition for 4 languages in both single corpus and cross corpus setting. Additionally, since multi-task learning (MTL) with gender, naturalness and arousal as auxiliary tasks has shown to enhance the generalisation capabilities of the emotion models, this paper introduces language ID as another auxiliary task in MTL …
Semantic-Emotional Resonance Embedding: A Semi-Supervised Paradigm for Cross-Lingual Speech Emotion Recognition
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Pengcheng Laboratory Xinjiang Network Node（鹏城实验室新疆网络节点）；Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术研究中心）；Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学具身智能联合研究实验室）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语言认知计算国际联合研究实验室）
Recent developments in speech emotion recognition (SER) often leverage deep neural networks (DNNs). Comparing and benchmarking different DNN models can often be tedious due to the use of different datasets and evaluation protocols. To facilitate the process, here, we present the Speech Emotion Recognition Adaptation Benchmark (SERAB), a framework for evaluating the performance and generalization capacity of different approaches for utterance-level SER. The benchmark is composed of nine datasets for SER in six languages. Since the datasets have different sizes and numbers of emotional classes, …
University of Southern Queensland（南昆士兰大学）；Information Technology University (ITU)（信息技术大学）；University of the West of England (UWE)（西英格兰大学）
Cross-lingual speech emotion recognition (SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become more apparent when training and test data belong to different languages, which cause a significant performance gap between the validation and test scores. It is imperative to build more robust models that can fit in practical applications of SER systems. Therefore, in this paper, we propose a Generative Adversarial Network (GAN)-based model for multilingual …
Technical University of Denmark（丹麦技术大学）；Copenhagen University Hospital（哥本哈根大学医院）；Copenhagen University（哥本哈根大学）
In recent years, speech emotion recognition (SER) has been used in wide ranging applications, from healthcare to the commercial sector. In addition to signal processing approaches, methods for SER now also use deep learning techniques which provide transfer learning possibilities. However, generalizing over languages, corpora and recording conditions is still an open challenge. In this work we address this gap by exploring loss functions that aid in transferability, specifically to non-tonal languages. We propose a variational autoencoder (VAE) with KL annealing and a semi-supervised VAE to ob…
This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to …
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the robustness of the system and reduce human labeling costs. In this study, we introduce an unsupervised Adversarial Discriminative Domain Adaptation (ADDA) method to effectively learn an asymmetric mapping that adapts the target domain encoder to the source domain, where the target domain and source domain are speech data from different languages. ADDA, together w…
(Short version of Abstract) This thesis describes an investigation on unsupervised acoustic modeling (UAM) for automatic speech recognition (ASR) in the zero-resource scenario, where only untranscribed speech data is assumed to be available. UAM is not only important in addressing the general problem of data scarcity in ASR technology development but also essential to many non-mainstream applications, for examples, language protection, language acquisition and pathological speech assessment. The present study is focused on two research problems. The first problem concerns unsupervised discover…
This work explores the effect of gender and linguistic-based vocal variations on the accuracy of emotive expression classification. Emotive expressions are considered from the perspective of spectral features in speech (Mel-frequency Cepstral Coefficient, Melspectrogram, Spectral Contrast). Emotions are considered from the perspective of Basic Emotion Theory. A convolutional neural network is utilised to classify emotive expressions in emotive audio datasets in English, German, and Italian. Vocal variations for spectral features assessed by (i) a comparative analysis identifying suitable spect…
This study addresses unsupervised subword modeling, i.e., learning feature representations that can distinguish subword units of a language. The proposed approach adopts a two-stage bottleneck feature (BNF) learning framework, consisting of autoregressive predictive coding (APC) as a front-end and a DNN-BNF model as a back-end. APC pretrained features are set as input features to a DNN-BNF model. A language-mismatched ASR system is used to provide cross-lingual phone labels for DNN-BNF model training. Finally, BNFs are extracted as the subword-discriminative feature representation. A second ai…
This study addresses unsupervised subword modeling, i.e., learning acoustic feature representations that can distinguish between subword units of a language. We propose a two-stage learning framework that combines self-supervised learning and cross-lingual knowledge transfer. The framework consists of autoregressive predictive coding (APC) as the front-end and a cross-lingual deep neural network (DNN) as the back-end. Experiments on the ABX subword discriminability task conducted with the Libri-light and ZeroSpeech 2017 databases showed that our approach is competitive or superior to state-of-…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Amazon Alexa（亚马逊Alexa）
Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how unsupervised representation learning on unlabeled datasets can benefit SER. We show that the contrastive predictive coding (CPC) method can learn salient representations from unlabeled datasets, which improves emotion recognition performance. In our experiments, this method achieved state-of-the-art concordance correlation coefficient (CCC) performance for all em…
National Laboratory of Pattern Recognition, CASIA, Beijing, China（中国科学院自动化研究所模式识别国家重点实验室，北京，中国）；CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China（中国科学院脑科学与智能技术卓越创新中心，北京，中国）；School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京，中国）
Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples. However, these methods pay less attention to modeling the long-term dynamic dependency, which is important for speech emotion recognition. To deal with this problem, this paper combines the unsupervised representation learning strategy -- Future Observation Prediction (FOP), with transfer learning approaches (such as Fine-tuning and Hypercolumns). To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results dem…
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the ta…
Facebook AI Research（Facebook人工智能研究院）；Ecole des Hautes Etudes en Sciences Sociales（社会科学高等研究院）
Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently, contrastive predictive coding (CPC) algorithms have been proposed to pretrain ASR systems with unlabelled data. In this work, we investigate whether unsupervised pretraining transfers well across languages. We show that a slight modification of the CPC pretraining extracts features that transfer well to other languages, being on par or even outperforming su…
This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish subword-level speech units. The proposed feature representations comprise various types of multilingual bottleneck features (BNFs) that are obtained via multi-task learning of deep neural networks (MTL-DNN). One of the key problems is how to acquire high-quality frame labels for untranscribed training data to facilitate supervised DNN training. It is shown th…
The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence, CUHK（香港中文大学感知与交互智能中心）；Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems（清华-香港中文大学媒体科学、技术与系统联合研究中心）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tsinghua University（清华大学）
We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by $β$-VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations show…
Polytechnic School of Pernambuco, University of Pernambuco（伯南布哥大学伯南布哥理工学院）；Federal University of Pernambuco（伯南布哥联邦大学）
The proposed model is only for the audio module. All videos in the OMG Emotion Dataset are converted to WAV files. The proposed model makes use of semi-supervised learning for the emotion recognition. A GAN is trained with unsupervised learning, with another database (IEMOCAP), and part of the GAN structure (part of the autoencoder) will be used for the audio representation. The audio spectrogram will be extracted in 1-second windows of 16khz frequency, and this will serve as input to the model of audio representation trained with another database in an unsupervised way. This audio representat…
Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
Instituto de Biociências, Letras e Ciências Exatas Universidade Estadual Paulista "Júlio de Mesquita Filho" (UNESP)（生物科学、文学和精确科学学院 帕尔马斯州立大学 "Júlio de Mesquita Filho" (UNESP)）
University of Sheffield（谢菲尔德大学）；Emotech Labs（Emotech实验室）
For speech emotion datasets, it has been difficult to acquire large quantities of reliable data and acted emotions may be over the top compared to less expressive emotions displayed in everyday life. Lately, larger datasets with natural emotions have been created. Instead of ignoring smaller, acted datasets, this study investigates whether information learnt from acted emotions is useful for detecting natural emotions. Cross-corpus research has mostly considered cross-lingual and even cross-age datasets, and difficulties arise from different methods of annotating emotions causing a drop in per…
