Natural speech can be easily manipulated to alter perception.
problem The susceptibility of natural speech to manipulation.
method Investigation of the McGurk effect and Yanny or Laurel illusion.
result A significant fraction of natural speech is illusionable.
DGP learns speech recognition by modeling complex relationships between utterances.
problem Modeling complex relationships in speech recognition without relational data.
method Bayesian nonparametric deep learning method (DGP) that generates infinite probabilistic graphs.
result DGP successfully infers relationships among utterances without relational data during training.
Study shows current metrics for audio adversarial examples are unreliable for human perception.
problem The reliability of metrics for evaluating audio adversarial examples.
method Analytical framework and human evaluation experiment.
result Current metrics for audio adversarial examples are not reliable for human perception.
Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model optimization criterion and the evaluation criterion on the enhanced speech. For …
We address the problem of bootstrapping language acquisition for an artificial system similarly to what is observed in experiments with human infants. Our method works by associating meanings to words in manipulation tasks, as a robot interacts with objects and listens to verbal descriptions of the interactions. The mo…
Unsupervised model generates distinct intonation codes for speech synthesis.
problem Lack of understanding of what prosodic variations are controlled in speech synthesis.
method Phrase-level variational autoencoder with multi-modal prior, using mode centres as intonation codes.
result Generated intonation codes are perceptually distinct and carry various affect-related styles.
A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty. The past decade has seen major advances in many perception tasks such as visual ob…
Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes longer. Current language models often struggle to keep track of coherence for long pi…
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for gene…
STRODE learns timings and dynamics from unlabeled time series data.
problem Learning dynamics of random event timings from unlabeled sensory inputs.
method Probabilistic Ordinary Differential Equation (STRODE) that samples from posterior point processes.
result Successfully infers event timings from synthetic and real-world datasets.
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…
Study the tradeoff between signal distortion and human perception over finite channels.
problem Characterize the distortion-perception tradeoff for finite channels with arbitrary metrics.
method Solve linear programming problems to compute the distortion-perception function and optimal reconstructions.
result DP function is piecewise linear in the perception index.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
End-to-end autonomous driving perception learns latent features for better performance.
problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.
Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musical…
Geometric model explains music perception combining neuroscience and acoustics.
problem Rationalize and predict psycho-acoustic phenomena in music perception.
method Combining neuroscientific theories with acoustic observations, a geometric model of the space of all chords is created.
result The geometric model allows for rigorous studies of psychoacoustic quantities like roughness and harmonicity.
Safe control for vehicles using learned perception from images.
problem Controlling autonomous vehicles with partial state information from images.
method Learned perception map and safe set design for a closed loop system.
result Generalization properties of the perception-control loop are favorable.
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
RETR improves indoor radar perception with a novel transformer model.
problem Indoor radar perception lacks models tailored for multi-view radar settings.
method RETR extends DETR architecture with depth-prioritized feature similarity, tri-plane loss, and radar-to-camera transformation.
result RETR outperforms state-of-the-art methods by 15.38+ AP for object detection and 11.91+ IoU for instance segmentation.
Researchers study how teachers' advising relationships influence their perceptions of satisfaction and students, not policy influence.
problem Understanding the relationship between teachers' advising relationships and their perceptions of satisfaction and students.
method Proposed a novel joint model of network and item responses (JNIRM) with correlated latent variables.
result Teachers' advising relationships contribute more to satisfaction and students than to influence over educational policies.
Study how actions affect perception in embodied agents using group theory.
problem Understanding how actions influence perception in autonomous agents.
method Mathematical formalism of group theory applied to sensory commutativity of action sequences.
result Introduced Sensory Commutativity Probability (SCP) to measure action effects on perception.
Paper shows continuous speech recognition with EEG features, no speech input.
problem Continuous speech recognition with limited vocabulary and noisy/no speech input.
method Connectionist temporal classification (CTC) model, EEG features, new deep learning architecture.
result Continuous speech recognition achieved on limited vocabulary with noisy/no speech input.
Reconstruction-based learning produces uninformative features for perception tasks.
problem Misalignment between reconstruction-based learning and perception tasks.
method Investigated the impact of input space reconstruction on feature learning for perception tasks.
result Reconstruction-based learning allocates model capacity to a subspace with uninformative features for perception tasks.
This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis pr…
RUSLAN is a large Russian speech corpus for text-to-speech.
problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.
AeGAN improves speech clarity in noisy environments.
problem Improving speech recognition in crowded noisy environments.
method Generative adversarial networks (GAN) with a novel architecture.
result The proposed framework outperforms traditional and learning-based methods.
Detects AI-synthesized speech using cepstral and bispectral analysis.
problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.
The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. This paper demonstrates that using electroencephalography (EEG) can help automatic speech recognition systems overcome performance loss in the presence of noise. The paper also shows that distillation training of auto…
Study uses deep learning to predict gender and analyze HPV vaccine perceptions on Twitter.
problem Analyzing gender differences in public perceptions on HPV vaccine using social media data.
method Convolutional neural network model trained on Twitter text for gender prediction, then applied to HPV vaccine related tweets.
result Identified gender differences in public perceptions on HPV vaccine, consistent with previous studies.
Tensor models decode human perception and memory using SPO triples.
problem Understanding implicit and explicit perception and memory in the brain.
method Tensor models with SPO triples, dual representations, and four layers.
result Semantic memory is crucial for explicit perception and declarative memories.
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
AudioPaLM combines text and speech models to improve speech processing and translation.
problem Improving speech understanding and generation models.
method Unified multimodal architecture combining text and speech models.
result AudioPaLM significantly outperforms existing speech translation systems.
Study examines perceptions and attitudes about breast cancer on Twitter.
problem Understanding public perceptions and attitudes towards breast cancer on social media.
method Identified and collected tweets, used topic modeling and sentiment analysis.
result Identified themes and quantified users' perceptions and emotions about breast cancer.
Enhances spoken speech quality using EEG signals.
problem Improves speech clarity in noisy environments.
method Generative adversarial network (GAN), gated recurrent unit (GRU), temporal convolutional network (TCN) regression models.
result Significant improvement in speech enhancement quality compared to traditional methods.
PeL separates sensory interface optimization from decision learning.
problem Optimizing sensory interfaces without task-specific information.
method Formal separation of perception and decision learning, using metrics for stability, informativeness, and geometry.
result Updates preserving invariants are orthogonal to decision gradients.
WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an autoregressive model and high-quality speech synthesis with the adversarial training. However, the …
Improved speech enhancement using diffusion models with MSE loss.
problem Efficient incorporation of noisy speech in generative speech enhancement.
method Augmented diffusion-based generative model with a MSE loss for enhanced speech.
result Proposed method improves speech enhancement performance compared to original diffusion model.
Logical scaffolds enhance AI software quality.
problem Improving AI component quality in software.
method Logical scaffolds as a method to improve AI components.
result Logical scaffolds can improve AI beyond perception systems.
PERCEPT detects changes in high-dimensional data streams using topological data analysis.
problem Detecting changes in high-dimensional data streams, especially when embedded in a low-dimensional space.
method Leverages topological data analysis to learn embedded topology as a point cloud via persistence diagrams, then applies non-parametric monitoring for detecting changes.
result Demonstrates efficient detection of online changes from high-dimensional data streams.
This work disentangles speech and non-speech components from found data.
problem Building robust acoustic models from found data with non-standard variations.
method Latent Stochastic Models and Multinode Latent Space Variational Autoencoders (VAE).
result Speech and music can be separated in the latent space of a VAE, independent of the language.
Sensorimotor contingency theory offers a promising account of the nature of perception, a topic rarely addressed in the robotics community. We propose a developmental framework to address the problem of the autonomous acquisition of sensorimotor contingencies by a naive robot. While exploring the world, the robot inter…
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
Speech emotion recognition system using features and text.
problem Improving accuracy in emotion recognition from speech.
method Used speech features (Spectrogram, MFCC) and text, trained Deep Neural Networks.
result Combined MFCC-Text CNN model achieved highest accuracy.
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.
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, an…
While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep …
Enhanced text-to-speech synthesizes expressive speech from a single example.
problem Creating a new expressive speech style from a single example of speech.
method Combines VAE and Normalizing Flows to improve disentanglement and naturalness.
result Reduces KL-divergence by 22% and improves perceptual metrics.
Default-ERM shortcut learning persists even without additional information.
problem Default-ERM shortcut learning in perception tasks despite stable feature sufficiency.
method Studied linear perception task; developed margin control (MARG-CTRL) loss functions.
result Margin control mitigates shortcut learning on various tasks.