Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

10192938 · Apr 201919922001200920182026
48 results for speech prosody

Paper proposes a new model for speech synthesis with better interpretability.

problem Improving interpretability in speech synthesis models.
method Hierarchical, fine-grained latent variable model with conditional variational auto-encoder (VAE).
result The new model allows better interpretability without degrading performance.

Improves naturalness in TTS samples using quantized VAE and auto-regressive prosody.

problem Discontinuous and unnatural speech from standard VAE priors.
method Discretized latent features using vector quantization (VQ), and separately trained autoregressive (AR) prior model.
result Significantly improves naturalness in random sample generation.

Generative models produce varied intonation in speech synthesis.

problem Typical TTS systems lack the ability to produce multiple distinct renditions of a sentence.
method Use variational autoencoders (VAEs) to capture a distribution over multiple renditions and produce varied intonation.
result Sampling from the tails of the VAE prior produces more varied intonation than traditional approaches, while maintaining naturalness.

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.

Improved F0 contour estimation from noisy speech with higher frequency resolution.

problem Estimating the fundamental frequency contour of speech from noisy audio.
method Regression model using recurrent deep neural networks trained on supervised learning.
result Improves F0 contour estimation by more than 25% at SNRs between -10 dB and +10 dB.

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.

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.

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.

Improved visual speech synthesis using adapted ASR acoustic models.

problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.

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.

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.

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.

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.

Diffusion models enhance speech without supervision.

problem Challenges in generalizing supervised speech enhancement methods to unseen conditions.
method Unsupervised speech enhancement using diffusion-based generative models.
result Demonstrates promising results compared to supervised and unsupervised baselines.

Speech enhancement improved by adapting to unknown speakers without auxiliary signals.

problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.

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.

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.

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.

Paper explores EEG-based speech recognition using transformers, showing faster training and better performance for smaller vocabularies.

problem Continuous speech recognition using EEG features.
method Transformer-based ASR model compared to RNN-based models.
result Transformer models perform better for smaller vocabularies but RNN models outperform them for larger vocabularies.

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.

VoiceFilter-Lite separates speech from background in real-time for on-device speech recognition.

problem Separate speech from background in real-time for on-device speech recognition.
method Asymmetric loss, adaptive runtime suppression, quantization to 8-bit.
result VoiceFilter-Lite achieves real-time speech separation and maintains speech recognition performance.

Enhances speech recognition in new environments by embedding noise and scaling training data.

problem Improving speech recognition in unseen noisy environments.
method Embedding noise from unseen environments and scaling training data to 16,784 environments.
result Reduced word error rate from 34.04% to 15.46% on enhanced speech.

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.

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.

Large receptive field CNNs improve distant speech recognition.

problem Degrading performance of ASR systems in noisy environments.
method Investigated large receptive field CNN variants including recursive, dilated, and hourglass networks.
result Stacked hourglass networks show significant improvements in distant speech recognition.

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.