VAE learns latent speech emotion features for classification.
problem Learning effective features for speech emotion recognition.
method Variational Autoencoders (VAEs) for generating latent speech emotion representations.
result VAEs produce state-of-the-art results for speech emotion classification.
WaveCycleGAN converts synthetic speech to natural speech using cycle-consistent adversarial networks.
problem Over-smoothing effect in synthetic speech, leading to quality degradation.
method Cycle-consistent adversarial networks for waveform-level modification.
result Improves naturalness of generated speech sounds.
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.
Study shows integrating acoustic features in financial forecasting models can degrade performance.
problem Predicting stock market volatility from corporate earnings calls using speech features.
method Empirical investigation of acoustic feature extraction in teleconference environments using a two-stream late-fusion architecture.
result Integrating acoustic features via late fusion significantly degraded performance, reducing recall to 47.08%.
ResNet with Focal Loss improves speech emotion recognition.
problem Speech emotion recognition using plain text features is insufficient.
method Residual Convolutional Neural Network (ResNet) trained with Focal Loss.
result Focal Loss enhances model's focus on hard examples.
RawNet synthesizes speech without relying on human-designed features.
problem Speech synthesis models rely heavily on human-designed spectral features.
method End-to-end neural vocoder using auto-encoder structure, learning features and audio recovery directly from raw waveform.
result RawNet achieves better speech quality with a simplified model architecture and faster inference speed.
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.
Synthetic speech data improves keyword spotting models with fewer real examples.
problem Training models for recognizing spoken keywords with limited real data.
method Used a pre-trained speech embedding model to extract features for training a small keyword spotting model.
result A model trained on synthetic speech data can detect 10 keywords with the same accuracy as a model trained on over 500 real examples.
Quaternion CNNs improve speech recognition with fewer parameters.
problem Efficient end-to-end speech recognition with minimal parameters.
method Integrating quaternion algebra into CNNs for speech feature processing.
result Quaternion CNNs achieve lower phoneme error rates with fewer parameters.
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.
Introspects convolutional speech recognition models using Gradient-adjusted Neuron Activation Profiles.
problem Lack of interpretability in deep learning ASR models.
method Gradient-adjusted Neuron Activation Profiles (GradNAPs) for feature and representation visualization.
result Gains insight into how data is processed in convolutional ASR models.
Speech synthesis from EEG features using RNN.
problem Speech synthesis from EEG data.
method Recurrent Neural Network (RNN) regression model to predict acoustic features from EEG features.
result Feasibility of synthesizing speech directly from EEG features demonstrated.
Improves speech separation by integrating time and frequency domains.
problem Speech separation using deep learning techniques.
method Proposes a framework that combines time and frequency domain features, using an embedding network and clustering.
result Obtained state-of-the-art results on WSJ0-2mix dataset.
SwishNet improves speech, music, and noise classification and segmentation.
problem Speech, Music, and Noise classification/segmentation for audio processing.
method Proposes a fast and lightweight 1D CNN (SwishNet) for MFCC features, trained with knowledge distillation from ImageNet.
result Achieved high accuracy (>97% clip classification, >93% frame-wise segmentation) on MUSAN corpus.
This paper introduces a method to select and weight pretext tasks for better self-supervised speech representation learning.
problem Combining pretext tasks for better performance in self-supervised speech representation learning.
method Estimating calibrated weights for partial losses corresponding to pretext tasks during self-supervised training.
result Groups of selected and weighted pretext tasks perform better than classic baselines in automatic speech recognition and speaker/emotion recognition.
Paper proposes i-vector approach for NLI with improved accuracy.
problem Identifying a speaker's native language from speech in a second language.
method i-vector approach using MFCC and GFCC features.
result Improved accuracy in NLI system, especially with GFCC features.
Neural model detects phoneme boundaries from speech, outperforming baselines.
problem Phoneme boundary detection for speech processing applications.
method Learnable segmental features with a structured loss function.
result Model achieves state-of-the-art performance on TIMIT and Buckeye corpora.
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.
CRBM extracts speech features from complex spectra directly.
problem Speech coding ignores phase information in complex spectra.
method CRBM learns relationships between visible and hidden units from complex-valued spectra.
result CRBM outperforms conventional methods in speech coding.
Quaternion neural networks improve speech recognition efficiency.
problem Improving speech recognition systems with fewer parameters.
method Investigating quaternion-valued convolutional and recurrent neural networks.
result Quaternion neural networks outperform real-valued models with fewer parameters.
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.
Paper proposes a CNN for speech emotion recognition using center loss and reconstruction.
problem Speech emotion recognition (SER) in audio signals.
method Convolutional Neural Network (CNN) with center loss and reconstruction as regularizers.
result Proposed method achieves highly discriminative features for SER.
Telephonetic improves robustness of neural language models to ASR errors.
problem Handling ASR errors and semantic noise in neural language models trained on written text.
method Data augmentation framework using character-level and embedding space perturbations.
result Achieves state-of-the-art perplexity of 37.49 on Penn Treebank corpus.
End-to-end model detects articulatory features from speech data.
problem Detecting articulatory features from speech data for various applications.
method Apply Listen, Attend and Spell (LAS) architecture and attention models.
result End-to-end training of manners and places of articulation detectors.
Deep architecture learns transferable features for robust speech emotion recognition.
problem Robust and discriminative features for diverse speech emotion domains.
method Jointly uses CNN for domain-shared features and LSTM for domain-specific emotion classification.
result Transferable features provide gains up to 18.4% in speech emotion recognition.
Anti-transfer learning prevents misleading representations for speech tasks.
problem Misleading representations learned from orthogonal tasks in speech processing.
method Penalizes similarity between activations of a network and another trained on an orthogonal task.
result Improves classification accuracy and invariance to the orthogonal task.
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
New HMC method handles features in POS tagging, outperforming MEMM.
problem HMC struggles with arbitrary features in POS tagging.
method Introduced Entropic Forward-Backward (EFB) probabilities to compute HMC restorations.
result EFB-based HMC outperforms MEMM in POS tagging.
Activates speech DNNs to generate understandable examples.
problem Difficulty in understanding DNN classifications for speech.
method Activation maximization to generate speech samples.
result Activation maximization can generate understandable speech samples.
ADReSS Challenge at INTERSPEECH 2020 benchmarks speech recognition for Alzheimer's dementia.
problem Automated recognition of Alzheimer's dementia from spontaneous speech.
method Provides a benchmark speech dataset, defines two tasks (classification and regression), and presents baseline models.
result Demonstrates the feasibility of automated speech recognition for Alzheimer's dementia.
WaveCRN improves E2E speech enhancement with efficient CNN and SRU.
problem Efficiently modeling speech locality and sequential properties for E2E speech enhancement.
method WaveCRN uses a CNN for speech locality and SRU for temporal sequential modeling, with RFM for noise suppression.
result WaveCRN outperforms state-of-the-art approaches with reduced complexity and inference time.
Enhanced transformer converts whispered speech to natural speech.
problem Machine recognition of whispered speech is challenging.
method Proposes an enhanced transformer architecture trained end-to-end using supervised learning.
result Similar formant distributions of converted speech to groundtruth.
Paper improves EEG-based speech recognition using CTC and beam search.
problem Improving continuous speech recognition from EEG signals.
method Implemented CTC-based ASR system, initialized weights, used external language model, studied articulatory feature prediction.
result Enhanced performance of EEG-based speech recognition systems.
New neural network design improves speech enhancement metrics.
problem Improving speech enhancement metrics in noisy conditions.
method Combination of convolutional and recurrent layers in U-net architecture.
result Proposed solution outperforms current state-of-the-art in SDR, SIR, and STOI metrics.
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.
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.
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.
Enhances speech from reverberated and noisy signals using Wide Residual Networks.
problem Improving intelligibility of speech from reverberated and noisy signals.
method Wide Residual Network architecture with residual connections for processing contextually correlated representations.
result Enhanced speech from the proposed method succeeded for both enhancement and speech recognition tasks.
Approach to detect emotion from speech using majority voting and selected features.
problem Detecting human emotion from speech.
method Majority voting technique over machine learning models (NN, DT, SVM, KNN).
result Majority voting technique achieves better accuracy than individual models.
Study shows adding noise to training data improves speech synthesis system's performance under noisy test conditions.
problem Impact of noisy linguistic features on neural network-based speech synthesis systems.
method Comparison of systems using ideal and corrupted linguistic features in training and test sets.
result Adding noise to training data can regularize the model and improve performance under noisy test conditions.
Enhanced speech emotion recognition using nonlinear recurrence dynamics.
problem Improving speech emotion recognition accuracy.
method Phase space reconstruction, Recurrence Plot, Recurrence Quantification Analysis, statistical functionals, feature fusion, Bidirectional Recurrent Neural Network.
result State-of-the-art performance on IEMOCAP with up to 10.7% improvement in accuracy.
End-to-end speech recognition system trained on GPUs and CPUs.
problem Building state-of-the-art speech recognition systems.
method Utilizes CPUs and GPUs for training, data augmentation, and neural network updates. Uses vocal tract length perturbation and acoustic simulator for data augmentation. Employed Horovod allreduce for training.
result Achieved 7.92% WER on proprietary English Bixby open domain test set using a Bidirectional Full Attention (BFA) model.
New RFs reduce kernel approximation variance and improve Transformer performance.
problem Efficient approximation of Gaussian and softmax kernels for kernel methods and Transformers.
method Parameterized, positive, non-trigonometric RFs optimized for variance reduction.
result Significant variance reduction in practice, outperforming previous methods.
QRNN and QLSTM improve speech recognition with fewer parameters.
problem Speech recognition with multi-dimensional input features.
method Quaternion algebra for modeling internal and external dependencies.
result QRNN and QLSTM achieve better performance with fewer parameters.
New speech recognition method uses hypergraphs for better label prediction.
problem Missed information in pairwise relationships between speech samples.
method Hypergraph Laplacian based semi-supervised learning methods applied to speech recognition.
result Sensitivity performance measures of hypergraph methods are better than state-of-the-art methods.
WaveNet reconstructs speech from brain activity, revealing acoustic features.
problem Reconstructing speech from brain activity with limited data.
method WaveNet model applied to STG intracranial recordings.
result WaveNet models reveal phoneme-level acoustic features.
Paper predicts EEG features from acoustic features using RNN and GAN.
problem Predicting EEG features from acoustic features.
method Recurrent Neural Network (RNN) and Generative Adversarial Network (GAN).
result Lower RMSE and normalized RMSE values compared to generating acoustic features from EEG features.
Survey reviews code-switched speech and language processing.
problem Processing code-switched text and speech for multilingual communities.
method Reviews computational approaches and lists available resources.
result Essential for building intelligent agents that interact in multilingual settings.