Stochastic WaveNet models sequential data with latent variables and dilated convolutions.
problem Modeling distribution of sequential data like speech and motions.
method Combines stochastic latent variables and dilated convolutions in WaveNet architecture.
result Obtains state-of-the-art performances on speech and handwriting datasets.
Proposes a speaker-independent GlotNet vocoder using WaveNet for speech generation.
problem Lack of efficient multi-speaker WaveNet models with limited resources.
method Uses source-filter model of speech production to train a WaveNet for glottal excitation.
result Proposed GlotNet vocoder performs favorably to direct WaveNet vocoder in speech quality.
NSF models generate speech waveforms faster and better than WaveNet.
problem Efficiently generating speech waveforms for statistical parametric synthesis.
method Neural source-filter (NSF) models that combine sine-based excitation, non-AR filter, and conditional preprocessing.
result NSF models generate waveforms 100 times faster than WaveNet and have better quality.
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.
A faster neural waveform model for speech synthesis.
problem Slow waveform generation in existing neural models.
method Proposes a non-autoregressive neural source-filter model.
result Generated waveforms 100 times faster than AR WaveNet.
Express Wavenet reduces neural network parameters to 1% of standard networks.
problem Optical neural networks with high parameter count.
method Wavelet modulation, random shift wavelets, expressway structure.
result Express Wavenet achieves high accuracy with significantly fewer parameters.
Neural network VQ-VAE with WaveNet decodes speech at 1.6 kbps with high quality.
problem Efficiently transmitting and storing speech signals at low bit-rates.
method VQ-VAE and WaveNet architecture for speech coding.
result Speech coding at 1.6 kbps with perceptual quality between MELP and AMR-WB.
TimbreTron transfers musical timbre using CQT and WaveNet.
problem Transfer musical timbre while preserving pitch, rhythm, and loudness.
method Apply image domain style transfer to CQT representation, then generate high-quality waveform with WaveNet.
result TimbreTron recognizably transfers timbre while preserving musical content.
Joint training model for TTS and VC tasks using Tacotron and WaveNet.
problem Training a shared model for text-to-speech and voice conversion.
method Extended Tacotron model with dual attention mechanism for shared tasks, WaveNet for waveform generation.
result Joint training of a shared model achieves both TTS and VC tasks efficiently.
Neural model synthesizes music with flexible timbre controls.
problem Creating audio samples with varied timbres from musical scores.
method Recurrent neural network conditioned on learned instrument embedding followed by WaveNet vocoder.
result Learned embedding space captures diverse timbres and enables interpolation for morphing.
WaveGlow generates high-quality speech from spectrograms.
problem Speech synthesis quality and efficiency.
method WaveGlow combines Glow and WaveNet insights, using a single network and cost function for efficient, high-quality audio synthesis.
result WaveGlow produces audio samples at over 500 kHz, matching WaveNet quality.
Improved multi-speaker TTS using GANs and waveform loss.
problem Training acoustic models for neural vocoders in multi-speaker TTS systems.
method Proposed frameworks incorporating Wasserstein GAN with gradient penalty (WGAN-GP) and discretized mixture logistic loss (DML) into acoustic models trained with WaveNet.
result Acoustic models trained with WGAN-GP and DML loss achieve highest subjective evaluation scores in multi-speaker TTS.
GANSynth uses GANs to efficiently synthesize high-fidelity audio.
problem Efficient and high-fidelity audio synthesis is challenging.
method Model log magnitudes and instantaneous frequencies with GANs.
result GANSynth outperforms WaveNet on automated and human evaluation metrics.
Unsupervised learning of speech representations using WaveNet autoencoders.
problem Extract meaningful latent representations of speech signals.
method Applying autoencoding neural networks to speech waveforms, using a high capacity WaveNet decoder, and comparing three variants of latent representations.
result Comparable performance with top entries in the ZeroSpeech 2017 unsupervised acoustic unit discovery task.
This study improves text-to-speech synthesis using GANs for glottal excitation.
problem Slow inference and computational cost of WaveNet and difficulty in parallel training of GANs.
method Adopted GANs for parallel waveform generation in speech signal and glottal excitation.
result GAN-based glottal excitation model achieves quality and voice similarity on par with WaveNet.
Graph WaveNet models spatial-temporal graphs by learning hidden dependencies and long sequences.
problem Capturing hidden spatial dependencies and long-range temporal sequences in graphs.
method Graph WaveNet integrates adaptive dependency matrix learning and stacked dilated 1D convolution.
result Graph WaveNet outperforms existing methods on public traffic network datasets.
This paper compares new speech synthesis methods and finds Wavenet vocoders and AR models perform best.
problem Improving speech synthesis quality using advanced machine learning techniques.
method Large-scale crowdsourced evaluation of vocoding and acoustic modeling techniques.
result Wavenet vocoders and AR models outperform conventional methods in speech synthesis quality.
Meta-learning approach for adaptive TTS with few data.
problem Adapting TTS systems to new speakers with minimal data.
method Meta-learning with shared WaveNet core and independent speaker embeddings, using three training strategies.
result Successful adaptation of multi-speaker neural network to new speakers with minimal data.
Combines symbolic and raw audio models for structured, realistic-sound music generation.
problem Lack of long-range dependencies in raw audio models and unstructured music.
method Uses a Long Short Term Memory network for melodic structure and WaveNet for raw audio generation with symbolic conditioning.
result Creates structured, realistic-sounding compositions using both symbolic and raw audio models.
WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.
problem Human ear can still distinguish synthesized speech from natural speech.
method WaveCycleGAN2 uses generators without down/up-sampling modules and combines discriminators from waveform and acoustic parameter domains.
result WaveCycleGAN2 achieves high-quality speech synthesis with comparable mean opinion scores to natural speech.
A method speeds up generation in convolutional autoregressive models.
problem Slow generation in convolutional autoregressive models.
method Cache hidden states to avoid redundant computation.
result Up to 21x and 183x speedups in generation for Wavenet and PixelCNN++ models.
Universal music translation network across instruments and genres.
problem Translating music across different instruments, genres, and styles.
method Multi-domain wavenet autoencoder with a shared encoder and disentangled latent space trained end-to-end on waveforms.
result Achieves convincing translations even from domains not seen during training.
New findings on how convolutional architectures approximate time series data.
problem Understanding the approximation properties of convolutional architectures in time series modeling.
method Mathematical analysis of convolutional architectures applied to time series modeling.
result A new definition of spectrum-based regularity for measuring temporal relationships under convolutional approximation.
Improved audio classification with limited labels using multitask and self-supervised learning.
problem Limited labeled data for audio classification.
method Multitask learning and self-supervised learning on unlabeled data.
result Significant improvement in performance (up to 6%) through multitask and self-supervised learning.
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.
This research improves neural synthesizers for music sounds from speech data.
problem Applying speech synthesis techniques to musical instrument sounds.
method Comparison of three neural synthesizers in three scenarios: training, zero-shot learning, and fine-tuning.
result Neural synthesizers trained on speech data and fine-tuned on music data perform better.
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
problem Voice conversion between speakers with limited parallel audio pairs.
method Hierarchical sequence to sequence model with attention-based decoder, trained on single speaker dataset.
result Improved voice conversion quality using mel spectrograms and wavenet vocoder.
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
problem Efficiently modeling long-term dependencies in sequences.
method Causal U-Net architecture with dilated filters and slow feature hypothesis.
result Seq-U-Net achieves comparable performance with speed-ups of over 4x in audio generation.
Study improves low-quality speech data for voice cloning.
problem Feasibility of training spoofing systems with low-quality data.
method Developed a GAN-based speech enhancement system, trained TTS and voice conversion models.
result Significant improvement in SNR and perceptual cleanliness of low-quality data.
SING generates musical notes from instruments in real-time.
problem Efficiently generating high-quality audio from MIDI data.
method Frame-by-frame waveform generation with a single decoder, using a new loss function.
result SING produces significantly improved audio quality compared to state-of-the-art models, with 32x faster training and 2,500x faster inference.
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.
NAF combines neural networks with autoregressive models for better density estimation.
problem Improving density estimation and speech synthesis speed.
method Generalizes autoregressive models using neural networks for invertible transformations.
result NAF is a universal approximator for continuous probability distributions and outperforms IAF.
Proposes a neural network for estimating traffic density uncertainty.
problem Lack of uncertainty estimates in deep learning traffic prediction models.
method Quantile Graph Wavenet, a Spatio-Temporal neural network trained to estimate density.
result Produces uncertainty estimates efficiently without sampling.
DiffWave generates high-fidelity audio waveforms efficiently.
problem Conditional and unconditional audio waveform generation.
method Non-autoregressive diffusion model using Markov chain synthesis.
result DiffWave produces high-quality audios in various tasks.
Deep learning converts one singer's voice to another without supervision.
problem Unsupervised singing voice conversion.
method Deep learning network with a single CNN encoder, WaveNet decoder, and classifier.
result Natural, recognizable singing voices converted without supervision.
PixelCNN models can achieve state-of-the-art results on CIFAR-10 with exact likelihood computation.
problem Dequantization gap in modeling discrete data like images.
method Introducing subset flows to allow exact computation of likelihoods for discrete data.
result PixelCNN models trained with exact likelihood computation achieve state-of-the-art results on CIFAR-10.
Efficient keyword spotting model using dilated convolutions and gating.
problem Keyword spotting in resource-constrained environments.
method End-to-end temporal modeling with dilated convolutions, gated activations, and residual connections.
result Our model outperforms LSTM-based keyword spotting with a significant decrease in false rejection rate.
Deep learning predicts mental disorders from audio and text samples.
problem Predicting mental disorders from speech samples.
method Multimodal deep learning structure using various pre-trained models for audio and text embeddings, transfer learning, and auxiliary corpora.
result Acceptable accuracy in predicting mental disorders through multimodal analysis.
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.
Improved time series forecasting with expert loss integration.
problem Enhancing time series forecasting accuracy and efficiency.
method Adaptive Mixture-of-Experts framework with expert-specific loss integration and online learning.
result Significantly improved forecasting accuracy and computational efficiency.
Survey of deep learning methods for forex and stock price prediction.
problem Improving accuracy and return in financial prediction.
method Classification of papers based on different deep learning methods.
result Recent models combining LSTM with other methods yield great returns and performances.
Efficient method improves neural network device placement.
problem Challenging task of placing operations on suitable devices in neural networks.
method End-to-end scalable sequential attention mechanism over graph neural network.
result 16% improvement over human experts and 9.2% over prior art.
Convolutional neural networks improve time series forecasting efficiency.
problem Efficiently forecasting multivariate time series with historical data.
method Adapted WaveNet architecture with dilated convolutions and parallel filters.
result Convolutional network outperforms autoregressive and LSTM models.
Enhanced Tacotron for Japanese speech synthesis improves naturalness.
problem Challenges in end-to-end Japanese speech synthesis due to pitch accents.
method Extended Tacotron with self-attention to capture pitch accent dependencies.
result Proposed systems show improvements but still lag behind traditional pipeline methods.
trVAE improves conditional out-of-sample generation for unpaired data.
problem Challenges in generating high-dimensional samples conditional on low-dimensional descriptors out-of-sample.
method trVAE uses maximum mean discrepancy (MMD) to match distributions across conditions in the decoder layer.
result Improved robustness and accuracy in predicting cellular perturbation responses and disease.
Deep learning models estimate black hole merger parameters and post-merger properties.
problem Estimating masses and properties of black hole mergers.
method Modified WaveNet architecture with contrastive learning and normalizing flow.
result Deep learning models produce statistically consistent results and similar posterior distributions to traditional Bayesian methods.
Paper proposes a method to create smaller, more efficient deep generative audio models.
problem High computation cost and complexity of deep generative models in audio applications.
method Developed a method for structured trimming of deep generative audio models.
result 95% of model weights can be removed without significant degradation in accuracy.