2023-06-22 更新
Enhancing the Prediction of Emotional Experience in Movies using Deep Neural Networks: The Significance of Audio and Language
Authors:Sogand Mehrpour Mohammadi, Meysam Gouran Orimi, Hamidreza Rabiee
Our paper focuses on making use of deep neural network models to accurately predict the range of human emotions experienced during watching movies. In this certain setup, there exist three clear-cut input modalities that considerably influence the experienced emotions: visual cues derived from RGB video frames, auditory components encompassing sounds, speech, and music, and linguistic elements encompassing actors’ dialogues. Emotions are commonly described using a two-factor model including valence (ranging from happy to sad) and arousal (indicating the intensity of the emotion). In this regard, a Plethora of works have presented a multitude of models aiming to predict valence and arousal from video content. However, non of these models contain all three modalities, with language being consistently eliminated across all of them. In this study, we comprehensively combine all modalities and conduct an analysis to ascertain the importance of each in predicting valence and arousal. Making use of pre-trained neural networks, we represent each input modality in our study. In order to process visual input, we employ pre-trained convolutional neural networks to recognize scenes[1], objects[2], and actions[3,4]. For audio processing, we utilize a specialized neural network designed for handling sound-related tasks, namely SoundNet[5]. Finally, Bidirectional Encoder Representations from Transformers (BERT) models are used to extract linguistic features[6] in our analysis. We report results on the COGNIMUSE dataset[7], where our proposed model outperforms the current state-of-the-art approaches. Surprisingly, our findings reveal that language significantly influences the experienced arousal, while sound emerges as the primary determinant for predicting valence. In contrast, the visual modality exhibits the least impact among all modalities in predicting emotions.
PDF
点此查看论文截图
LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models
Authors:Zhichao Wang, Yuanzhe Chen, Lei Xie, Qiao Tian, Yuping Wang
Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explore the feasibility of LMs for zero-shot voice conversion. An intuitive approach is to follow AudioLM - Tokenizing speech into semantic and acoustic tokens respectively by HuBERT and SoundStream, and converting source semantic tokens to target acoustic tokens conditioned on acoustic tokens of the target speaker. However, such an approach encounters several issues: 1) the linguistic content contained in semantic tokens may get dispersed during multi-layer modeling while the lengthy speech input in the voice conversion task makes contextual learning even harder; 2) the semantic tokens still contain speaker-related information, which may be leaked to the target speech, lowering the target speaker similarity; 3) the generation diversity in the sampling of the LM can lead to unexpected outcomes during inference, leading to unnatural pronunciation and speech quality degradation. To mitigate these problems, we propose LM-VC, a two-stage language modeling approach that generates coarse acoustic tokens for recovering the source linguistic content and target speaker’s timbre, and then reconstructs the fine for acoustic details as converted speech. Specifically, to enhance content preservation and facilitates better disentanglement, a masked prefix LM with a mask prediction strategy is used for coarse acoustic modeling. This model is encouraged to recover the masked content from the surrounding context and generate target speech based on the target speaker’s utterance and corrupted semantic tokens. Besides, to further alleviate the sampling error in the generation, an external LM, which employs window attention to capture the local acoustic relations, is introduced to participate in the coarse acoustic modeling.
PDF
点此查看论文截图
SURT 2.0: Advances in Transducer-based Multi-talker Speech Recognition
Authors:Desh Raj, Daniel Povey, Sanjeev Khudanpur
The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR). Despite impressive results on multi-turn meetings, SURT has notable limitations: (i) it suffers from leakage and omission related errors; (ii) it is computationally expensive, due to which it has not seen adoption in academia; and (iii) it has only been evaluated on synthetic mixtures. In this work, we propose several modifications to the original SURT which are carefully designed to fix the above limitations. In particular, we (i) change the unmixing module to a mask estimator that uses dual-path modeling, (ii) use a streaming zipformer encoder and a stateless decoder for the transducer, (iii) perform mixture simulation using force-aligned subsegments, (iv) pre-train the transducer on single-speaker data, (v) use auxiliary objectives in the form of masking loss and encoder CTC loss, and (vi) perform domain adaptation for far-field recognition. We show that our modifications allow SURT 2.0 to outperform its predecessor in terms of multi-talker ASR results, while being efficient enough to train with academic resources. We conduct our evaluations on 3 publicly available meeting benchmarks — LibriCSS, AMI, and ICSI, where our best model achieves WERs of 16.9%, 44.6% and 32.2%, respectively, on far-field unsegmented recordings. We release training recipes and pre-trained models: https://sites.google.com/view/surt2.
PDF 13 pages, 6 figures. Project webpage: https://sites.google.com/view/surt2
点此查看论文截图
Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition
Authors:Yuchen Hu, Ruizhe Li, Chen Chen, Chengwei Qin, Qiushi Zhu, Eng Siong Chng
Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most existing efforts still focus on audio modality to improve robustness considering its dominance in AVSR task, with noise adaptation techniques such as front-end denoise processing. Though effective, these methods are usually faced with two practical challenges: 1) lack of sufficient labeled noisy audio-visual training data in some real-world scenarios and 2) less optimal model generality to unseen testing noises. In this work, we investigate the noise-invariant visual modality to strengthen robustness of AVSR, which can adapt to any testing noises while without dependence on noisy training data, a.k.a., unsupervised noise adaptation. Inspired by human perception mechanism, we propose a universal viseme-phoneme mapping (UniVPM) approach to implement modality transfer, which can restore clean audio from visual signals to enable speech recognition under any noisy conditions. Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach achieves the state-of-the-art under various noisy as well as clean conditions. In addition, we also outperform previous state-of-the-arts on visual speech recognition task.
PDF 19 pages, 9 figures, Accepted by ACL 2023
点此查看论文截图
MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition
Authors:Yuchen Hu, Chen Chen, Ruizhe Li, Heqing Zou, Eng Siong Chng
Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech. Mainstream approaches addressing this task have developed sophisticated architectures and techniques for multi-modality fusion and representation learning. However, the natural heterogeneity of different modalities causes distribution gap between their representations, making it challenging to fuse them. In this paper, we aim to learn the shared representations across modalities to bridge their gap. Different from existing similar methods on other multimodal tasks like sentiment analysis, we focus on the temporal contextual dependencies considering the sequence-to-sequence task setting of AVSR. In particular, we propose an adversarial network to refine frame-level modality-invariant representations (MIR-GAN), which captures the commonality across modalities to ease the subsequent multimodal fusion process. Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach outperforms the state-of-the-arts.
PDF 14 pages, 5 figures, Accepted by ACL 2023
点此查看论文截图
STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization
Authors:Kyle Min
This report introduces our novel method named STHG for the Audio-Visual Diarization task of the Ego4D Challenge 2023. Our key innovation is that we model all the speakers in a video using a single, unified heterogeneous graph learning framework. Unlike previous approaches that require a separate component solely for the camera wearer, STHG can jointly detect the speech activities of all people including the camera wearer. Our final method obtains 61.1% DER on the test set of Ego4D, which significantly outperforms all the baselines as well as last year’s winner. Our submission achieved 1st place in the Ego4D Challenge 2023. We additionally demonstrate that applying the off-the-shelf speech recognition system to the diarized speech segments by STHG produces a competitive performance on the Speech Transcription task of this challenge.
PDF Validation report for the Ego4D challenge at CVPR 2023
点此查看论文截图
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
Authors:Ziqiao Peng, Yihao Luo, Yue Shi, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan
Speech-driven 3D face animation technique, extending its applications to various multimedia fields. Previous research has generated promising realistic lip movements and facial expressions from audio signals. However, traditional regression models solely driven by data face several essential problems, such as difficulties in accessing precise labels and domain gaps between different modalities, leading to unsatisfactory results lacking precision and coherence. To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces. The framework constructs a network system consisting of three modules: facial animator, speech recognizer, and lip-reading interpreter. The core of SelfTalk is a commutative training diagram that facilitates compatible features exchange among audio, text, and lip shape, enabling our models to learn the intricate connection between these factors. The proposed framework leverages the knowledge learned from the lip-reading interpreter to generate more plausible lip shapes. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. We recommend watching the supplementary video.
PDF
点此查看论文截图
Rehearsal-Free Online Continual Learning for Automatic Speech Recognition
Authors:Steven Vander Eeckt, Hugo Van hamme
Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF). Continual Learning (CL) attempts to train ASR models without suffering from CF. While in ASR, offline CL is usually considered, online CL is a more realistic but also more challenging scenario where the model, unlike in offline CL, does not know when a task boundary occurs. Rehearsal-based methods, which store previously seen utterances in a memory, are often considered for online CL, in ASR and other research domains. However, recent research has shown that weight averaging is an effective method for offline CL in ASR. Based on this result, we propose, in this paper, a rehearsal-free method applicable for online CL. Our method outperforms all baselines, including rehearsal-based methods, in two experiments. Our method is a next step towards general CL for ASR, which should enable CL in all scenarios with few if any constraints.
PDF Accepted at INTERSPEECH 2023. 5 pages
点此查看论文截图
Quilt-1M: One Million Image-Text Pairs for Histopathology
Authors:Wisdom Oluchi Ikezogwo, Mehmet Saygin Seyfioglu, Fatemeh Ghezloo, Dylan Stefan Chan Geva, Fatwir Sheikh Mohammed, Pavan Kumar Anand, Ranjay Krishna, Linda Shapiro
Recent accelerations in multi-modal applications have been made possible with the plethora of image and text data available online. However, the scarcity of analogous data in the medical field, specifically in histopathology, has halted comparable progress. To enable similar representation learning for histopathology, we turn to YouTube, an untapped resource of videos, offering $1,087$ hours of valuable educational histopathology videos from expert clinicians. From YouTube, we curate Quilt: a large-scale vision-language dataset consisting of $768,826$ image and text pairs. Quilt was automatically curated using a mixture of models, including large language models, handcrafted algorithms, human knowledge databases, and automatic speech recognition. In comparison, the most comprehensive datasets curated for histopathology amass only around $200$K samples. We combine Quilt with datasets from other sources, including Twitter, research papers, and the internet in general, to create an even larger dataset: Quilt-1M, with $1$M paired image-text samples, marking it as the largest vision-language histopathology dataset to date. We demonstrate the value of Quilt-1M by fine-tuning a pre-trained CLIP model. Our model outperforms state-of-the-art models on both zero-shot and linear probing tasks for classifying new histopathology images across $13$ diverse patch-level datasets of $8$ different sub-pathologies and cross-modal retrieval tasks.
PDF
点此查看论文截图