AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
Universal audio perturbations fool ASR systems.
problem Speech recognition systems are vulnerable to adversarial attacks.
method Developed an algorithm to create universal perturbations that fool ASR models.
result Universal perturbations can fool ASR systems across different models.
Machine learning identifies species by voice in remote areas.
problem Continuous monitoring of endangered species in remote areas.
method Training machine learning models on audio data to recognize species.
result Machine learning can accurately classify and recognize various species sounds.
Deep Fusion improves audio-video emotion recognition accuracy.
problem Challenges in automatic emotion recognition due to abstract concept and multiple expressions of emotion.
method Introduces factorized bilinear pooling (FBP) with embedded attention mechanism to integrate audio and video features.
result Achieves an accuracy of 62.48% on AFEW database, outperforming state-of-the-art results.
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
Review of deep learning techniques for audio signal processing.
problem Improving audio signal processing using deep learning.
method Analysis of various deep learning models and techniques.
result Advancements in speech, music, and environmental sound processing.
This research tackles backdoor attacks on audio data using a stochastic investment approach.
problem The threat of backdoor attacks on audio data, especially in voice-activated systems.
method A Stochastic investment-based backdoor attack (MarketBack) approach.
result MarketBack can achieve an average attack success rate close to 100% with less than 1% of poisoned data.
The paper analyzes how speech enhancement and recognition can be improved in noisy environments.
problem Improving speech recognition in multi-talker scenarios with limited resources.
method Developed and trained two LSTM-based models for speech enhancement and phone recognition, then studied their joint optimization.
result Joint optimization of speech enhancement and recognition leads to a significant reduction in Phone Error Rate (PER).
Method generates audio attacks resistant to reverberation and noise.
problem Physical attacks on speech recognition models.
method Simulates playback and recording transformations to generate robust adversarial examples.
result Adversarial examples can attack speech recognition without being noticed by humans.
FSD50K provides an open dataset of over 51k audio clips for sound event recognition.
problem Small and domain-specific sound event recognition datasets.
method Creation of an open dataset with over 51k audio clips manually labeled using 200 classes.
result FSD50K is a new open benchmark for sound event recognition research.
This paper creates imperceptible, effective audio adversarial examples for speech recognition.
problem Current adversarial examples in speech recognition are easily detectable and ineffective in real-world settings.
method Developed imperceptible audio adversarial examples using psychoacoustic masking and simulated environmental distortions.
result Successfully created imperceptible, targeted adversarial examples for speech recognition that are effective in real-world settings.
Paper proposes ICCN to learn correlations between text, audio, and video for multimodal sentiment analysis.
problem Improving multimodal sentiment analysis by learning hidden correlations between text and audio/video features.
method Interaction Canonical Correlation Network (ICCN) using deep canonical correlation analysis (DCCA).
result Empirical results confirm the effectiveness of ICCN in capturing useful information from all three views.
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
Improved audio event recognition using audiovisual transformers.
problem Weakly labeled audio event classification with limited temporal information.
method Adapted transformer architecture that combines audio and video inputs.
result State-of-the-art performance on audiovisual data set.
SVM algorithm extracts digits from audio CAPTCHAs.
problem Recognizing audio CAPTCHAs from computer programs.
method Used RastaPLP features and SVM algorithm.
result Successfully extracted digits from audio CAPTCHAs.
New neural network improves audio classification accuracy.
problem Challenging audio classification problem in pattern recognition.
method Introduces a Classifier-Attention-Based Convolutional Neural Network (CAB-CNN) with an attention mechanism to reduce classifier complexity.
result Significantly improves audio classification performance, achieving more than 10% improvements.
The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition problem. In particular, we will build a model to determine whether a one second audio…
SpeechYOLO detects and locates speech objects in audio signals.
problem Detecting and localizing speech in audio signals.
method Inspired by YOLO, SpeechYOLO uses a convolutional neural network with a least-mean-squares loss function.
result SpeechYOLO performs well on keyword spotting tasks, including read and spontaneous speech.
A fusion approach combines audio and video features for emotion recognition.
problem Continuous emotion recognition using both visual and auditory modalities.
method Pre-trained CNN features from video frames and minimalistic auditory descriptors. Fusion at feature or prediction level. SVR for prediction.
result Improves CCCs of 0.749 and 0.565 for arousal and valence respectively.
Detects audio adversarial examples using anomalous pattern detection.
problem Identifies adversarial audio attacks in deep neural networks.
method Applies anomalous pattern detection in activation space of audio models.
result Can detect adversarial examples with up to 0.98 AUC, no degradation on benign samples.
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
Adversarial training improves audio classifier robustness.
problem Improving robustness of audio classifiers against adversarial attacks.
method Adversarial training of deep neural networks on audio data.
result Adversarially trained models can resist higher perturbations and fooling rates.
Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align…
Vehicle recognition and classification have broad applications, ranging from traffic flow management to military target identification. We demonstrate an unsupervised method for automated identification of moving vehicles from roadside audio sensors. Using a short-time Fourier transform to decompose audio signals, we t…
AVEC 2019 challenges AI in detecting depression and cross-cultural emotions.
problem Detecting depression and cross-cultural emotions from audiovisual data.
method Comparison of machine learning methods under standardized conditions.
result Baseline system performance on state-of-mind, depression, and cross-cultural tasks.
Meta-learning improves few-shot acoustic event detection.
problem Detecting new audio events with limited labeled data.
method Formulated few-shot AED problem; explored supervised and meta-learning approaches.
result Meta-learning achieves superior performance in few-shot AED.
Paper presents an audiovisual model to recognize sounds from weakly labeled video data.
problem Sound recognition from weakly labeled video data.
method Audiovisual fusion model with attention mechanism.
result The model achieves a mean Average Precision (mAP) of 46.16 on AudioSet, outperforming state-of-the-art models.
End-to-end ASR error detection using audio-transcript entailment.
problem Detecting transcription errors in ASR systems to prevent error propagation.
method Proposes a novel end-to-end approach using audio-transcript entailment, with acoustic and linguistic encoders.
result Achieves CER of 26.2% on all transcription errors and 23% on medical errors specifically, improving by 12% and 15.4% respectively over a strong baseline.
This paper describes audEERING's submissions as well as additional evaluations for the One-Minute-Gradual (OMG) emotion recognition challenge. We provide the results for audio and video processing on subject (in)dependent evaluations. On the provided Development set, we achieved 0.343 Concordance Correlation Coefficien…
Two-stream model recognizes affect from audio and video.
problem Human affect recognition in real-world settings.
method Two-stream aural-visual analysis model with separate audio and visual processing.
result Model achieves promising results on Aff-Wild2 database.
Study improves animal audio classification using data augmentation.
problem Improving automated animal audio classification accuracy.
method Exploits different data augmentation techniques for training CNNs.
result Best recognition rates on animal audio classification datasets.
Paper proposes DPN for encrypted speech recognition, maintaining privacy and security.
problem Privacy and security issues in cloud-based speech recognition.
method Deep Polynomial Network (DPN) for encrypted speech, cloud-local joint decoding.
result DPN can make frame-level predictions over encrypted speech and return them in encrypted form.
Speech emotion recognition improved with simpler machine learning models.
problem Identifying emotions from speech is ambiguous and challenging.
method Feature-engineering approach using hand-crafted audio features and text features. Comparison of traditional machine learning and deep learning models.
result Lighter machine learning models outperform deep learning models for emotion recognition.
The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fool…
We here summarize our experience running a challenge with open data for musical genre recognition. Those notes motivate the task and the challenge design, show some statistics about the submissions, and present the results.
Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Spee…
Enhances speech emotion recognition by integrating visual data with attention mechanisms.
problem Improving emotion detection accuracy by combining multiple modalities.
method Introducing an attention mechanism to combine audio, text, and video modalities.
result Significant improvement of 3.65% in weighted accuracy.
Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inpu…
This research converts visual information into audio for users to perceive.
problem Brevity in conveying visual information through spoken language.
method Pretrained image embedding network, GAN for metric space mapping, human subject testing.
result Users can accurately classify audio sonifications of faces.
Paper explores deep learning features for complex emotion recognition.
problem Improving emotion recognition accuracy in complex emotions.
method Used pretrained networks (AudioSet Net, VoxCeleb Net, Deep Speech Net) and their deep layer features for emotion recognition.
result Achieved highest F1 score of 0.85 on EmoReact dataset.
Robust ASR model removes fast-changing features to resist attacks.
problem Vulnerability of ASR systems to adversarial attacks.
method Removing fast-changing features using slow feature analysis or low-pass filtering.
result Hybrid ASR models are more than four times more robust against targeted attacks.
We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) designed for temporal signal recognition. The CLNN takes into consideration the temporal nature of the sound signal and the MCLNN extends upon the CLNN through a binary mask to preserve the spatial locality of the feature…
Self-paced ensemble learning improves audio classification models.
problem Improving performance of individual models in speech and audio classification.
method A self-paced ensemble learning scheme where models learn from each other over several iterations.
result SPEL significantly outperforms baseline ensemble models.
In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable. Active learning aims to label only the most informative samples to reduce cost. For speech recognition, confidence scores and other likelihood-based active learning methods have been shown to be effectiv…
A scalable system learns acoustic models from 1 Million hours of untranscribed audio.
problem Learning acoustic models from large, untranscribed audio datasets.
method Semi-supervised learning with a student/teacher learning paradigm, focusing on the data and model pipelines.
result Relative accuracy improvements of 10-20% in noisy conditions, with no extensive hyper-parameter tuning.
New dataset for evaluating speech recognition fairness across demographics.
problem Lack of fairness metrics in speech recognition datasets.
method Developed Fair-Speech dataset with diverse demographic information.
result Helps evaluate ASR models for fairness across demographics.
Novel fusion of autoencoders predicts sleepiness from speech.
problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.