LSSED: a large-scale dataset and benchmark for speech emotion recognition

Fan, Weiquan; Xu, Xiangmin; Xing, Xiaofen; Chen, Weidong; Huang, Dongyan

doi:10.48550/arxiv.2102.01754

Cited by 3 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For speech synthesis, various datasets are available for different tasks. LSSED [11] is a challenging large-scale English speech emotion dataset, which has data collected from 820 subjects to simulate real-world distribution. AISHELL-3 [36] contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese speakers, which could be applied for multi-speaker speech synthesis.…”

Section: Speechmentioning

confidence: 99%

Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus

Huang

Chen

Ren

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

High-fidelity multi-singer singing voice synthesis is challenging for neural vocoder due to the singing voice data shortage, limited singer generalization, and large computational cost. Existing open corpora could not meet requirements for high-fidelity singing voice synthesis because of the scale and quality weaknesses. Previous vocoders have difficulty in multi-singer modeling, and a distinct degradation emerges when conducting unseen singer singing voice generation. To accelerate singing voice researches in the community, we release a large-scale, multi-singer Chinese singing voice dataset OpenSinger. To tackle the difficulty in unseen singer modeling, we propose Multi-Singer, a fast multi-singer vocoder with generative adversarial networks. Specifically, 1) Multi-Singer uses a multi-band generator to speed up both training and inference procedure. 2) to capture and rebuild singer identity from the acoustic feature (i.e., mel-spectrogram), Multi-Singer adopts a singer conditional discriminator and conditional adversarial training objective.3) to supervise the reconstruction of singer identity in the spectrum envelopes in frequency domain, we propose an auxiliary singer perceptual loss. The joint training approach effectively works in GANs for multi-singer voices modeling. Experimental results verify the effectiveness of OpenSinger and show that Multi-Singer improves unseen singer singing voices modeling in both speed and quality over previous methods. The further experiment proves that combined with FastSpeech 2 as the acoustic model, Multi-Singer achieves strong robustness in the multi-singer singing voice synthesis pipeline. Samples are available at https://Multi-Singer.github.io/ CCS CONCEPTS• Applied computing → Sound and music computing; • Computing methodologies → Natural language generation.

show abstract

Section: Speechmentioning

confidence: 99%

Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus

Huang

Chen

Ren

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…ESD [21] is the first parallel multi-lingual and multi-speaker emotional speech dataset designed for voice conversion tasks and contains five emotional classes in each language. LSSED [22] is a large English dataset designed for SER tasks, which have a nine-classes emotion annotation. EmoV-DB [23] is the first dataset designed for emotional TTS tasks.…”

Section: Introductionmentioning

confidence: 99%

EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model

Cui

Ren

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the stateof-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 efficient architecture for emotional speech synthesis called EMSpeech. Unlike those models which need additional reference audio as input, our model could predict emotion labels just from the input text and generate more expressive speech conditioned on the emotion embedding. In the experiment phase, we first validate the effectiveness of our dataset by an emotion classification task. Then we train our model on the proposed dataset and conduct a series of subjective evaluations. Finally, by showing a comparable performance in the emotional speech synthesis task, we successfully demonstrate the ability of the proposed model.

show abstract

“…They pretrained their novel DNN-based models with 90,000 unlabeled utterances, and fine-tuned and evaluated them on 3,000 randomly selected manually annotated utterances from the same dataset. Fan et al [14] presented a SER dataset with a total duration of over 200 hours. They proposed a novel SER model containing pyramid convolutions which outperformed other models that were tested on the dataset.…”

Section: Introductionmentioning

confidence: 99%

Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit

Vaaras¹,

Ahlqvist‐Björkroth²,

Drossos³

et al. 2021

Preprint

View full text Add to dashboard Cite

Researchers have recently started to study how the emotional speech heard by young infants can affect their developmental outcomes. As a part of this research, hundreds of hours of daylong recordings from preterm infants' audio environments were collected from two hospitals in Finland and Estonia in the context of so-called APPLE study. In order to analyze the emotional content of speech in such a massive dataset, an automatic speech emotion recognition (SER) system is required. However, there are no emotion labels or existing indomain SER systems to be used for this purpose. In this paper, we introduce this initially unannotated large-scale real-world audio dataset and describe the development of a functional SER system for the Finnish subset of the data. We explore the effectiveness of alternative state-of-the-art techniques to deploy a SER system to a new domain, comparing cross-corpus generalization, WGAN-based domain adaptation, and active learning in the task. As a result, we show that the best-performing models are able to achieve a classification performance of 73.4% unweighted average recall (UAR) and 73.2% UAR for a binary classification for valence and arousal, respectively. The results also show that active learning achieves the most consistent performance compared to the two alternatives.

show abstract

LSSED: a large-scale dataset and benchmark for speech emotion recognition

Cited by 3 publications

References 25 publications

Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus

Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus

EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model

Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit

Contact Info

Product

Resources

About