This paper presents our investigations on emotional state categorization from speech signals with a psychologically inspired computational model against human performance under the same experimental setup. Based on psychological studies, we propose a multistage categorization strategy which allows establishing an automatic categorization model flexibly for a given emotional speech categorization task. We apply the strategy to the Serbian Emotional Speech Corpus (GEES) and the Danish Emotional Speech Corpus (DES), where human performance was reported in previous psychological studies. Our work is the first attempt to apply machine learning to the GEES corpus where the human recognition rates were only available prior to our study. Unlike the previous work on the DES corpus, our work focuses on a comparison to human performance under the same experimental settings. Our studies suggest that psychology-inspired systems yield behaviours that, to a great extent, resemble what humans perceived and their performance is close to that of humans under the same experimental setup. Furthermore, our work also uncovers some differences between machine and humans in terms of emotional state recognition from speech.
We present a methodology to train our multi-speaker emotional text-to-speech synthesizer that can express speech for 10 speakers' 7 different emotions. All silences from audio samples are removed prior to learning. This results in fast learning by our model. Curriculum learning is applied to train our model efficiently. Our model is first trained with a large single-speaker neutral dataset, and then trained with neutral speech from all speakers. Finally, our model is trained using datasets of emotional speech from all speakers. In each stage, training samples of each speaker-emotion pair have …
National University of Singapore (NUS)（新加坡国立大学）；Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）
Emotional voice conversion (EVC) aims to change the emotional state of an utterance while preserving the linguistic content and speaker identity. In this paper, we propose a novel 2-stage training strategy for sequence-to-sequence emotional voice conversion with a limited amount of emotional speech data. We note that the proposed EVC framework leverages text-to-speech (TTS) as they share a common goal that is to generate high-quality expressive voice. In stage 1, we perform style initialization with a multi-speaker TTS corpus, to disentangle speaking style and linguistic content. In stage 2, w…
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）
Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network conditioned on discrete representation, such as one-hot emotion labels. Such networks learn to remember a fixed set of emotional styles. In this paper, we propose a novel framework based on variational auto-encoding Wasserstein generative adversarial network (VAW-GAN), which makes use of a pre-trained speech emotion recognition (SER) model to transfer emotio…
Université Tunis El Manar（突尼斯埃尔马纳尔大学）；Ecole Nationale d'Ingénieurs de Tunis-ENIT（突尼斯国家工程学院）
The purpose of speech emotion recognition system is to classify speakers utterances into different emotional states such as disgust, boredom, sadness, neutral and happiness. Speech features that are commonly used in speech emotion recognition rely on global utterance level prosodic features. In our work, we evaluate the impact of frame level feature extraction. The speech samples are from Berlin emotional database and the features extracted from these utterances are energy, different variant of mel frequency cepstrum coefficients, velocity and acceleration features.
Semantic Differentiation in Speech Emotion Recognition: Insights from Descriptive and Expressive Speech Roles
School of Electrical Engineering and Computer Science, University of Ottawa（电气工程与计算机科学学院，渥太华大学）；School of Psychology, University of Ottawa（心理学学院，渥太华大学）；National Research Council Canada, Ottawa, Canada（加拿大国家研究理事会，渥太华，加拿大）
Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is becoming a new challenge to researchers due to the scarcity of high-quality emotion speech dataset and the lack of advanced emotional TTS model. In this paper, we first briefly introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. After that, we propose a simple but ef…
Numediart Institute University of Mons（蒙斯大学Numediart研究所）
In this project, we aim to build a Text-to-Speech system able to produce speech with a controllable emotional expressiveness. We propose a methodology for solving this problem in three main steps. The first is the collection of emotional speech data. We discuss the various formats of existing datasets and their usability in speech generation. The second step is the development of a system to automatically annotate data with emotion/expressiveness features. We compare several techniques using transfer learning to extract such a representation through other tasks and propose a method to visualiz…
Gonzaga University（贡萨加大学）；Washington State University（华盛顿州立大学）
Syllables play an important role in speech synthesis, speech recognition, and spoken document retrieval. A novel, low cost, and language agnostic approach to dividing words into their corresponding syllables is presented. A hybrid genetic algorithm constructs a categorization of phones optimized for syllabification. This categorization is used on top of a hidden Markov model sequence classifier to find syllable boundaries. The technique shows promising preliminary results when trained and tested on English words.
TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
Department of Computer Science, Johns Hopkins University（约翰霍普金斯大学计算机科学系）；Department of Electrical and Computer Engineering, Johns Hopkins University（约翰霍普金斯大学电气与计算机工程系）；Amazon Research（亚马逊研究院）；Amazon（亚马逊）
Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）；National University of Singapore (NUS)（新加坡国立大学）；University of Bremen（不来梅大学）
Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years. However, the generated voice is often not perceptually identifiable by its intended emotion category. To address this problem, we propose a new interactive training paradigm for ETTS, denoted as i-ETTS, which seeks to directly improve the emotion discriminability by interacting with a speech emotion recognition (SER) model. Moreover, we formulate an iterative training strategy with reinforcement learning to ensure the quality of i-ETTS optimization. Experimental results demonstrate that the proposed i-ETTS outper…
In this work we try to perform emotional style transfer on audios. In particular, MelGAN-VC architecture is explored for various emotion-pair transfers. The generated audio is then classified using an LSTM-based emotion classifier for audio. We find that "sad" audio is generated well as compared to "happy" or "anger" as people have similar expressions of sadness.
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Islamic Azad University（伊斯兰阿扎德大学）
In this paper, we introduce an emotional speech synthesizer based on the recent end-to-end neural model, named Tacotron. Despite its benefits, we found that the original Tacotron suffers from the exposure bias problem and irregularity of the attention alignment. Later, we address the problem by utilization of context vector and residual connection at recurrent neural networks (RNNs). Our experiments showed that the model could successfully train and generate speech for given emotion labels.
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；University of Science and Technology of China（中国科学技术大学）
Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected. In this paper, we propose QI-TTS which aims to better transfer and control intonation to further deliver the speaker's questioning intention while transferring emotion from reference speech. We propose a multi-style extractor to extract style embedding from two different levels. While the sentence level represents emotion, the final syllable level represents intonation. For fine-grained intonation control, we use relative attributes to represent i…
Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset
Johns Hopkins University（约翰霍普金斯大学）；Carnegie Mellon University（卡内基梅隆大学）；The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Inner Mongolia University（内蒙古大学）
Harvey Mudd College（哈维穆德学院）；University of Southern California（南加州大学）；Institute for Creative Technologies（创意技术研究所）
Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states are often "overshadowed" by voice characteristics relating to emotional intensity or emotional activation. In this work we explore a representation learning approach that automatically derives discriminative representations of emotional speech. In particular, we investigate two machine learning strategies to improve classifier performance: (1) utilization of u…
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）
Emotional voice conversion (EVC) aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity. In this paper, we study the disentanglement and recomposition of emotional elements in speech through variational autoencoding Wasserstein generative adversarial network (VAW-GAN). We propose a speaker-dependent EVC framework based on VAW-GAN, that includes two VAW-GAN pipelines, one for spectrum conversion, and another for prosody conversion. We train a spectral encoder that disentangles emotion and prosody (F0) information from spectra…
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 Bremen（不来梅大学）
In this paper, we first provide a review of the state-of-the-art emotional voice conversion research, and the existing emotional speech databases. We then motivate the development of a novel emotional speech database (ESD) that addresses the increasing research need. With this paper, the ESD database is now made available to the research community. The ESD database consists of 350 parallel utterances spoken by 10 native English and 10 native Chinese speakers and covers 5 emotion categories (neutral, happy, angry, sad and surprise). More than 29 hours of speech data were recorded in a controlle…
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…
Max Planck Institute for Empirical Aesthetics（马克斯·普朗克经验美学研究所）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）
The human voice effectively communicates a range of emotions with nuanced variations in acoustics. Existing emotional speech corpora are limited in that they are either (a) highly curated to induce specific emotions with predefined categories that may not capture the full extent of emotional experiences, or (b) entangled in their semantic and prosodic cues, limiting the ability to study these cues separately. To overcome this challenge, we propose a new approach called 'Genetic Algorithm with People' (GAP), which integrates human decision and production into a genetic algorithm. In our design,…
KI for Artificial Intelligence, KAIST（韩国科学技术院人工智能研究所）；Information and Electronics Research Institute, KAIST（韩国科学技术院信息与电子研究所）
Voice conversion (VC) is a task to transform a person's voice to different style while conserving linguistic contents. Previous state-of-the-art on VC is based on sequence-to-sequence (seq2seq) model, which could mislead linguistic information. There was an attempt to overcome it by using textual supervision, it requires explicit alignment which loses the benefit of using seq2seq model. In this paper, a voice converter using multitask learning with text-to-speech (TTS) is presented. The embedding space of seq2seq-based TTS has abundant information on the text. The role of the decoder of TTS is…
In this paper, we propose a new methodology for emotional speech recognition using visual deep neural network models. We employ the transfer learning capabilities of the pre-trained computer vision deep models to have a mandate for the emotion recognition in speech task. In order to achieve that, we propose to use a composite set of acoustic features and a procedure to convert them into images. Besides, we present a training paradigm for these models taking into consideration the different characteristics between acoustic-based images and regular ones. In our experiments, we use the pre-traine…
In recent years, emotional text-to-speech has shown considerable progress. However, it requires a large amount of labeled data, which is not easily accessible. Even if it is possible to acquire an emotional speech dataset, there is still a limitation in controlling emotion intensity. In this work, we propose a novel method for cross-speaker emotion transfer and manipulation using vector arithmetic in latent style space. By leveraging only a few labeled samples, we generate emotional speech from reading-style speech without losing the speaker identity. Furthermore, emotion strength is readily c…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Text-based speech editing allows users to edit speech by intuitively cutting, copying, and pasting text to speed up the process of editing speech. In the previous work, CampNet (context-aware mask prediction network) is proposed to realize text-based speech editing, significantly improving the quality of edited speech. This paper aims at a new task: adding emotional effect to the editing speech during the text-based speech editing to make the generated speech more expressive. To achieve this task, we propose Emo-CampNet (emotion CampNet), which can provide the option of emotional attributes fo…
OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Tongyi Laboratory（通义实验室）；University of New South Wales（新南威尔士大学）；National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition（脑启发智能感知与认知重点实验室）
Centre for Speech Technology Research, University of Edinburgh（爱丁堡大学语音技术研究中心）
Self-supervised speech models have grown fast during the past few years and have proven feasible for use in various downstream tasks. Some recent work has started to look at the characteristics of these models, yet many concerns have not been fully addressed. In this work, we conduct a study on emotional corpora to explore a popular self-supervised model -- wav2vec 2.0. Via a set of quantitative analysis, we mainly demonstrate that: 1) wav2vec 2.0 appears to discard paralinguistic information that is less useful for word recognition purposes; 2) for emotion recognition, representations from th…
HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech
South China University of Technology, China（华南理工大学，中国）；Huya Inc., China（欢丫公司，中国）；Tongyi Fun Team, Alibaba Group, China（通义 Fun 团队，阿里巴巴集团，中国）；Foshan University, China（佛山大学，中国）
Speech-related Brain Computer Interfaces (BCI) aim primarily at finding an alternative vocal communication pathway for people with speaking disabilities. As a step towards full decoding of imagined speech from active thoughts, we present a BCI system for subject-independent classification of phonological categories exploiting a novel deep learning based hierarchical feature extraction scheme. To better capture the complex representation of high-dimensional electroencephalography (EEG) data, we compute the joint variability of EEG electrodes into a channel cross-covariance matrix. We then extra…
Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition
Fudan University（复旦大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Fujian University of Technology（福建工程学院）；Xiamen University（厦门大学）；Shanghai Center for Brain Science and Brain-Inspired Technology（上海脑科学与类脑研究中心）
