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

1.9%3.8%5.7%7.6% · Apr 201919922001200920182026
48 results for audio encoding

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.

New WildMix dataset and Spectro-Temporal Transformer model for better monoaural audio source separation.

problem Challenging monoaural audio source separation.
method Introducing WildMix dataset and Spectro-Temporal Transformer model (STT) with Spectro-Temporal Encoder (STE).
result STT outperforms previous baselines on the WildMix dataset.

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.

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.

GACELA fills long gaps in musical audio with a GAN and context conditioning.

problem Restoring long gaps in musical audio with varying complexity and duration.
method Generative adversarial network (GAN) with five parallel discriminators and context conditioning.
result Reduced artifacts in inpaintings from unacceptable to mildly disturbing.

Mobile devices learn audio representations using self-supervised methods.

problem Learning general-purpose audio representations on mobile devices.
method Temporal context exploitation in spectrogram domain, inspired by Word2Vec.
result Self-supervised models can produce embeddings that perform similarly to fully supervised models.

Synthesizes images from audio and visual data using spike-based autoencoders.

problem Extracting meaningful information from spatio-temporal data for image synthesis.
method Spike-based autoencoders trained to learn spatio-temporal representations of audio and visual data.
result Synthesized images from audio samples with high fidelity, achieving competitive performance.

Neural codec for high-fidelity audio compression.

problem Efficiently compress audio while maintaining high quality.
method End-to-end neural network architecture with quantized latent space, single multiscale spectrogram adversary, loss balancer mechanism, and lightweight Transformer compression.
result 40% compression with no loss in quality, faster than real-time.

Paper proposes a bijective approach for signal/symbol translation using variational auto-encoders.

problem Extracting symbolic information from signals, especially in music, is challenging and non-generic.
method Turned into a density estimation task, using two variational auto-encoders with additive constraint.
result Bijective signal/symbol translation achieved, allowing both signal-to-symbol and symbol-to-signal inference.

A new method controls synthesizers with normalizing flows for easier exploration and creation.

problem Complexity and parameters in modern synthesizers make them hard to master.
method Formalizing synthesizer control as latent audio space mapping with VAE and NF, disentangling flows.
result Superior performance in parameter inference and audio reconstruction, disentangling major audio variations.

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.

Proposes a Complex Transformer for complex-valued sequence modeling.

problem Lack of deep learning models for complex-valued data.
method Develops a Complex Transformer using transformer backbone with specialized attention and encoder-decoder networks.
result Achieves state-of-the-art performance on complex-valued datasets.

This paper improves sentiment classification by combining text, audio, and video data using DCCA.

problem Improving sentiment classification accuracy using multi-modal data.
method Deep Canonical Correlation Analysis (DCCA) for combining text, audio, and video embeddings.
result One-Step DCCA outperforms current state-of-the-art in multi-modal embedding learning.

Unified probabilistic models improve audio signal processing efficiency and interpretability.

problem High computational cost and difficulty in interpreting probabilistic models in time-frequency analysis.
method Equivalence to Spectral Mixture Gaussian processes, state space representation, Kalman smoothing, efficient parameter learning.
result Unified models make it easier to interpret and modify model assumptions.

Proposes a self-supervised method for generating spatial audio from monaural audio and video.

problem Generating spatial audio from monaural audio and video recordings is challenging and expensive.
method Uses a self-supervised network with an auxiliary classifier to classify video channels and generate spatial audio.
result The proposed method effectively generates spatial audio from monaural audio and video.

Study improves radio show segmentation using audio embeddings.

problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.

Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, th…

2018-02-09abs ↗pdf ↗

Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.

problem Susceptibility of audio classifiers to adversarial attacks on spectrograms.
method Applying adversarial attacks to spectrograms and reconstructing audio waveforms.
result Perturbed spectrograms can fool 2D CNNs and 1D CNNs trained on audio waveforms.

daep learns from irregular, multimodal astronomical data.

problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.

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.