skip to main content

Title: An Efficient Temporal Modeling Approach for Speech Emotion Recognition by Mapping Varied Duration Sentences into Fixed Number of Chunks
Speech emotion recognition (SER) plays an important role in multiple fields such as healthcare, human-computer interaction (HCI), and security and defense. Emotional labels are often annotated at the sentence-level (i.e., one label per sentence), resulting in a sequence-to-one recognition problem. Traditionally, studies have relied on statistical descriptions, which are com- puted over time from low level descriptors (LLDs), creating a fixed dimension sentence-level feature representation regardless of the duration of the sentence. However sentence-level features lack temporal information, which limits the performance of SER systems. Recently, new deep learning architectures have been proposed to model temporal data. An important question is how to extract emotion-relevant features with temporal infor- mation. This study proposes a novel data processing approach that extracts a fixed number of small chunks over sentences of different durations by changing the overlap between these chunks. The approach is flexible, providing an ideal frame- work to combine gated network or attention mechanisms with long short-term memory (LSTM) networks. Our experimental results based on the MSP-Podcast dataset demonstrate that the proposed method not only significantly improves recognition accuracy over alternative temporal-based models relying on LSTM, but also leads to computational efficiency.  more » « less
Award ID(s):
1823166 1453781
Author(s) / Creator(s):
Date Published:
Journal Name:
Interspeech 2020
Page Range / eLocation ID:
2322 to 2326
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    A critical issue of current speech-based sequence-to-one learning tasks, such as speech emotion recognition (SER), is the dynamic temporal modeling for speech sentences with different durations. The goal is to extract an informative representation vector of the sentence from acoustic feature sequences with varied length. Traditional methods rely on static descriptions such as statistical functions or a universal background model (UBM), which are not capable of characterizing dynamic temporal changes. Recent advances in deep learning architectures provide promising results, directly extracting sentence-level representations from frame-level features. However, conventional cropping and padding techniques that deal with varied length sequences are not optimal, since they truncate or artificially add sentence-level information. Therefore, we propose a novel dynamic chunking approach, which maps the original sequences of different lengths into a fixed number of chunks that have the same duration by adjusting their overlap. This simple chunking procedure creates a flexible framework that can incorporate different feature extractions and sentence-level temporal aggregation approaches to cope, in a principled way, with different sequence-to-one tasks. Our experimental results based on three databases demonstrate that the proposed framework provides: 1) improvement in recognition accuracy, 2) robustness toward different temporal length predictions, and 3) high model computational efficiency advantages. 
    more » « less
  2. Chunk-level speech emotion recognition (SER) is a common modeling scheme to obtain better recognition performance than sentence-level formulations. A key open question is the role of lexical boundary information in the process of splitting a sentence into small chunks. Is there any benefit in providing precise lexi- cal boundary information to segment the speech into chunks (e.g., word-level alignments)? This study analyzes the role of lexical boundary information by exploring alternative segmentation strategies for chunk-level SER. We compare six chunk-level segmentation strategies that either consider word-level alignments or traditional time-based segmentation methods by varying the number of chunks and the duration of the chunks. We conduct extensive experiments to evaluate these chunk-level segmentation approaches using multiples corpora, and multiple acoustic feature sets. The results show a minor contribution of the word-level timing boundaries, where centering the chunks around words does not lead to significant performance gains. Instead, the critical factor to effectively segment a sentence into data chunks is to define the number of chunks according to the number of spoken words in the sentence. 
    more » « less
  3. Speech emotion recognition (SER) is a challenging task due to the limited availability of real-world labeled datasets. Since it is easier to find unlabeled data, the use of self-supervised learning (SSL) has become an attractive alternative. This study proposes new pre-text tasks for SSL to improve SER. While our target application is SER, the proposed pre-text tasks include audio-visual formulations, leveraging the relationship between acoustic and facial features. Our proposed approach introduces three new unimodal and multimodal pre-text tasks that are carefully designed to learn better representations for predicting emotional cues from speech. Task 1 predicts energy variations (high or low) from a speech sequence. Task 2 uses speech features to predict facial activation (high or low) based on facial landmark movements. Task 3 performs a multi-class emotion recognition task on emotional labels obtained from combinations of action units (AUs) detected across a video sequence. We pre-train a network with 60.92 hours of unlabeled data, fine-tuning the model for the downstream SER task. The results on the CREMA-D dataset show that the model pre-trained on the proposed domain-specific pre-text tasks significantly improves the precision (up to 5.1%), recall (up to 4.5%), and F1-scores (up to 4.9%) of our SER system. 
    more » « less
  4. null (Ed.)
    Human-computer interactions can be very effective, especially if computers can automatically recognize the emotional state of the user. A key barrier for effective speech emotion recognition systems is the lack of large corpora annotated with emotional labels that reflect the temporal complexity of expressive behaviors, especially during multiparty interactions. This pa- per introduces the MSP-Conversation corpus, which contains interactions annotated with time-continuous emotional traces for arousal (calm to active), valence (negative to positive), and dominance (weak to strong). Time-continuous annotations offer the flexibility to explore emotional displays at different temporal resolutions while leveraging contextual information. This is an ongoing effort, where the corpus currently contains more than 15 hours of speech annotated by at least five annotators. The data is sourced from the MSP-Podcast corpus, which contains speech data from online audio-sharing websites annotated with sentence-level emotional scores. This data collection scheme is an easy, affordable, and scalable approach to obtain natural data with diverse emotional content from multiple speakers. This study describes the key features of the corpus. It also compares the time-continuous evaluations from the MSP- Conversation corpus with the sentence-level annotations of the MSP-Podcast corpus for the speech segments that overlap between the two corpora. 
    more » « less
  5. As an intuitive way of expression emotion, the animated Graphical Interchange Format (GIF) images have been widely used on social media. Most previous studies on automated GIF emotion recognition fail to effectively utilize GIF’s unique properties, and this potentially limits the recognition performance. In this study, we demonstrate the importance of human related information in GIFs and conduct humancentered GIF emotion recognition with a proposed Keypoint Attended Visual Attention Network (KAVAN). The framework consists of a facial attention module and a hierarchical segment temporal module. The facial attention module exploits the strong relationship between GIF contents and human characters, and extracts frame-level visual feature with a focus on human faces. The Hierarchical Segment LSTM (HSLSTM) module is then proposed to better learn global GIF representations. Our proposed framework outperforms the state-of-the-art on the MIT GIFGIF dataset. Furthermore, the facial attention module provides reliable facial region mask predictions, which improves the model’s interpretability. 
    more » « less