Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obtain new state-of-the-art results on the challenging IEMOCAP dataset.
Speaker Style-Aware Phoneme Anchoring for Improved Cross-Lingual Speech Emotion Recognition
Department of Electrical Engineering, National Tsing Hua University, Taiwan（National Tsing Hua University电子工程系）；Language Technologies Institute, Carnegie Mellon University, USA（卡内基梅隆大学语言技术研究所）
In this work, we explore the dependencies between speaker recognition and emotion recognition. We first show that knowledge learned for speaker recognition can be reused for emotion recognition through transfer learning. Then, we show the effect of emotion on speaker recognition. For emotion recognition, we show that using a simple linear model is enough to obtain good performance on the features extracted from pre-trained models such as the x-vector model. Then, we improve emotion recognition performance by fine-tuning for emotion classification. We evaluated our experiments on three differen…
Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific speakers and scenarios is needed, inevitably leading to poorer performances when compared to humans. In this paper, we present novel work based on the idea of teaching the emotion recognition network about speaker identity. Our system is a combination of two ACRNN classifiers respectively dedicated to speaker and emotion recognition. The first informs the latter…
This research aims at identifying the unknown emotion using speaker cues. In this study, we identify the unknown emotion using a two-stage framework. The first stage focuses on identifying the speaker who uttered the unknown emotion, while the next stage focuses on identifying the unknown emotion uttered by the recognized speaker in the prior stage. This proposed framework has been evaluated on an Arabic Emirati-accented speech database uttered by fifteen speakers per gender. Mel-Frequency Cepstral Coefficients (MFCCs) have been used as the extracted features and Hidden Markov Model (HMM) has …
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for each individual speaker, and non-homogeneous for distributions of different speakers. These irregular distributions can seriously impact speaker recognition performance, especially with the popular PLDA scoring method, which assumes homogeneous Gaussian distribution. In this paper, we argue that deep speaker vectors require deep normalization, and propose a de…
University of Southern California（南加州大学）；JD AI Research（京东人工智能研究院）
Representation learning for speech emotion recognition is challenging due to labeled data sparsity issue and lack of gold standard references. In addition, there is much variability from input speech signals, human subjective perception of the signals and emotion label ambiguity. In this paper, we propose a machine learning framework to obtain speech emotion representations by limiting the effect of speaker variability in the speech signals. Specifically, we propose to disentangle the speaker characteristics from emotion through an adversarial training network in order to better represent emot…
Osaka University（大阪大学）；Curtin University（科廷大学）；National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）；CyberAgent, Inc.（赛博代理公司）
Emotional voice conversion (VC) aims to convert a neutral voice to an emotional (e.g. happy) one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech information (such as speaker, content, etc.) is the key to achieving remarkable performance. Some recent attempts about speech representation decoupling on the neutral speech can not work well on the emotional speech, due to the more complex acoustic properties involved in the latter. To address this problem, here we propose a novel Source-Filter-based Emotional VC mo…
Expressive text-to-speech has shown improved performance in recent years. However, the style control of synthetic speech is often restricted to discrete emotion categories and requires training data recorded by the target speaker in the target style. In many practical situations, users may not have reference speech recorded in target emotion but still be interested in controlling speech style just by typing text description of desired emotional style. In this paper, we propose a text-based interface for emotional style control and cross-speaker style transfer in multi-speaker TTS. We propose t…
University of Augsburg（奥格斯堡大学）；University of Tokyo（东京大学）；Imperial College（帝国理工学院）
In this work, we explore a novel few-shot personalisation architecture for emotional vocalisation prediction. The core contribution is an `enrolment' encoder which utilises two unlabelled samples of the target speaker to adjust the output of the emotion encoder; the adjustment is based on dot-product attention, thus effectively functioning as a form of `soft' feature selection. The emotion and enrolment encoders are based on two standard audio architectures: CNN14 and CNN10. The two encoders are further guided to forget or learn auxiliary emotion and/or speaker information. Our best approach a…
In practical applications for emotion recognition, users do not always exist in the training corpus. The mismatch between training speakers and testing speakers affects the performance of the trained model. To deal with this problem, we need our model to focus on emotion-related information, while ignoring the difference between speaker identities. In this paper, we look into the use of the domain adversarial neural network (DANN) to extract a common representation between different speakers. The primary task is to predict emotion labels. The secondary task is to learn a common representation …
National Institute of Technology Patna（巴特那国家技术学院）；Central University of South Bihar（南比哈尔中央大学）
Speech is produced when time varying vocal tract system is excited with time varying excitation source. Therefore, the information present in a speech such as message, emotion, language, speaker is due to the combined effect of both excitation source and vocal tract system. However, there is very less utilization of excitation source features to recognize emotion. In our earlier work, we have proposed a novel method to extract glottal closure instants (GCIs) known as epochs. In this paper, we have explored epoch features namely instantaneous pitch, phase and strength of epochs for discriminati…
Probabilistic Linear Discriminant Analysis (PLDA) has become state-of-the-art method for modeling $i$-vector space in speaker recognition task. However the performance degradation is observed if enrollment data size differs from one speaker to another. This paper presents a solution to such problem by introducing new PLDA scoring normalization technique. Normalization parameters are derived in a blind way, so that, unlike traditional \textit{ZT-norm}, no extra development data is required. Moreover, proposed method has shown to be optimal in terms of detection cost function. The experiments co…
We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions. If, however, these conditions are not met, e.g. under data-set shift between training and runtime, our theory reveals dependencies between scores that could be exploited by strategies such as score normalization. Indeed, it has been demonstrated over and over experimentally, that various ad-hoc score normalization recipes do work. We present a first attempt at using probability theory to design a generative score-space normaliza…
The style of the speech varies from person to person and every person exhibits his or her own style of speaking that is determined by the language, geography, culture and other factors. Style is best captured by prosody of a signal. High quality multi-speaker speech synthesis while considering prosody and in a few shot manner is an area of active research with many real-world applications. While multiple efforts have been made in this direction, it remains an interesting and challenging problem. In this paper, we present a novel few shot multi-speaker speech synthesis approach (FSM-SS) that le…
Deep speaker embedding represents the state-of-the-art technique for speaker recognition. A key problem with this approach is that the resulting deep speaker vectors tend to be irregularly distributed. In previous research, we proposed a deep normalization approach based on a new discriminative normalization flow (DNF) model, by which the distributions of individual speakers are arguably transformed to homogeneous Gaussians. This normalization was demonstrated to be effective, but despite this remarkable success, we empirically found that the latent codes produced by the DNF model are generall…
University of Luxembourg（卢森堡大学）；Australian national university（澳大利亚国立大学）
We leverage different context windows when predicting the emotion of different utterances. New modules are included to realize variable-length context: 1) two speaker-aware units, which explicitly model inner- and inter-speaker dependencies to form distilled conversational context, and 2) a top-k normalization layer, which determines the most proper context windows from the conversational context to predict emotion. Experiments and ablation studies show that our approach outperforms several strong baselines on three public datasets.
Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the limitation that it can only convert the voice to the speakers in the training data, which narrows down the applicable scenario of VC. In this paper, we proposed a novel one-shot VC approach which is able to perform VC by only an example utterance from source and target speaker respectively, and the source and target speaker do not even need to be seen during tra…
In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-region through a learnable dictionary encoding layer. These embeddings are concatenated to obtain the final speaker representation. The SPE layer not only generates a fixed-dimensional speaker embedding for a variable-length speech segment, but also aggregates the information of …
Brno University of Technology（布尔诺理工大学）；NTT Corporation（日本电信电话株式会社）
Recently, the performance of blind speech separation (BSS) and target speech extraction (TSE) has greatly progressed. Most works, however, focus on relatively well-controlled conditions using, e.g., read speech. The performance may degrade in more realistic situations. One of the factors causing such degradation may be intrinsic speaker variability, such as emotions, occurring commonly in realistic speech. In this paper, we investigate the influence of emotions on TSE and BSS. We create a new test dataset of emotional mixtures for the evaluation of TSE and BSS. This dataset combines LibriSpeec…
One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power of the speaker embedding. However, the number of model parameters is relatively large and the unspecified variations increase in the multi-layer aggregation. Therefore, we propose a self-attentive multi-layer aggregation with feature recalibration and normalization for end-to-end speaker verification system. To reduce the number of model parameters, the Res…
Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are available. Although the quality of VC is crucial for this approach, it is challenging to learn a stable VC model because the amount of data is limited in low-resource scenarios, and highly expressive speech has large acoustic variety. To address this issue, we propose a novel data augmentation method that combines pitch-shifting and VC techniques. Because pitch-shift data augmentation enables the coverage of a variety of pit…
We propose a novel method for emotion conversion in speech based on a chained encoder-decoder-predictor neural network architecture. The encoder constructs a latent embedding of the fundamental frequency (F0) contour and the spectrum, which we regularize using the Large Diffeomorphic Metric Mapping (LDDMM) registration framework. The decoder uses this embedding to predict the modified F0 contour in a target emotional class. Finally, the predictor uses the original spectrum and the modified F0 contour to generate a corresponding target spectrum. Our joint objective function simultaneously optim…
Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from prosody sequences in training data or transferred from a source style. We propose a text to speech(TTS) system, where a user can choose the emotion of generated speech from a continuous and meaningful emotion space (Arousal-Valence space). The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion. We show th…
Coventry University（考文垂大学）；American University of Beirut（贝鲁特美国大学）
In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We accomplish this by using a novel convolutional layer that exploits both local and global spatial information, and a convolutional layer with a reduced number of parameters that exploits facial symmetry. Furthermore, we introduce a generative adversarial gradual greedy layer-wise learning algorithm designed to train Adversarial Autoencoders in an efficient and incremental manner…
NIST, ITL（美国国家标准与技术研究院信息技术实验室）；University of Maryland, College Park（马里兰大学帕克分校）
Automatic emotion recognition plays a key role in computer-human interaction as it has the potential to enrich the next-generation artificial intelligence with emotional intelligence. It finds applications in customer and/or representative behavior analysis in call centers, gaming, personal assistants, and social robots, to mention a few. Therefore, there has been an increasing demand to develop robust automatic methods to analyze and recognize the various emotions. In this paper, we propose a neural network-based emotion recognition framework that uses a late fusion of transfer-learned and fi…
National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）；University of Southern Queensland（南昆士兰大学）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）；University of Bremen（不来梅大学）
Emotional voice conversion (EVC) seeks to convert the emotional state of an utterance while preserving the linguistic content and speaker identity. In EVC, emotions are usually treated as discrete categories overlooking the fact that speech also conveys emotions with various intensity levels that the listener can perceive. In this paper, we aim to explicitly characterize and control the intensity of emotion. We propose to disentangle the speaker style from linguistic content and encode the speaker style into a style embedding in a continuous space that forms the prototype of emotion embedding.…
CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the fusion of the acoustic and lexical features. Then these fusion representations are fed into the self-attention based bi-directional gated recurrent unit (GRU) layer to capture long-term contextual information. To imitate real interaction patterns of different speakers, speaker embeddings are also utilized as additional inputs to distinguish the speaker ident…
MILA（米拉研究所）；Université de Montréal（蒙特利尔大学）；Samsung Advanced Institute of Technology（三星先进技术研究院）
Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, …
Dartmouth College（达特茅斯学院）；ProtagoLabs；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Generating context-aware language that embodies diverse emotions is an important step towards building empathetic NLP systems. In this paper, we propose a formulation of modulated layer normalization -- a technique inspired by computer vision -- that allows us to use large-scale language models for emotional response generation. In automatic and human evaluation on the MojiTalk dataset, our proposed modulated layer normalization method outperforms prior baseline methods while maintaining diversity, fluency, and coherence. Our method also obtains competitive performance even when using only 10%…
Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person's emotions are influenced by the other speaker's utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multimodal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (…
A language agnostic approach to recognizing emotions from speech remains an incomplete and challenging task. In this paper, we performed a step-by-step comparative analysis of Speech Emotion Recognition (SER) using Bangla and English languages to assess whether distinguishing emotions from speech is independent of language. Six emotions were categorized for this study, such as - happy, angry, neutral, sad, disgust, and fear. We employed three Emotional Speech Sets (ESS), of which the first two were developed by native Bengali speakers in Bangla and English languages separately. The third was a…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））
Datasets that capture the connection between vision, language, and affection are limited, causing a lack of understanding of the emotional aspect of human intelligence. As a step in this direction, the ArtEmis dataset was recently introduced as a large-scale dataset of emotional reactions to images along with language explanations of these chosen emotions. We observed a significant emotional bias towards instance-rich emotions, making trained neural speakers less accurate in describing under-represented emotions. We show that collecting new data, in the same way, is not effective in mitigating…
Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay, data augmentation and dropout, regularization based on multi-branch architectures, such as Shake-Shake regularization, has been proven successful in many applications and attracted more and more attention. However, beyond model-based representation augmentation, it is unclear how Shake-Shake regularization helps to provide further improvement on classification…
