Automatically identifies vehicles from audio sensors without needing labeled data.
problem Vehicle recognition and classification from acoustic signals.
method Incremental reseeding of acoustic signatures using spectral embedding and clustering.
result Incremental reseeding accurately identifies individual vehicles from their acoustic signatures.
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is…
We propose a method for recognizing moving vehicles, using data from roadside audio sensors. This problem has applications ranging widely, from traffic analysis to surveillance. We extract a frequency signature from the audio signal using a short-time Fourier transform, and treat each time window as an individual data …
Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied with classification or regression engines which condition on this (often low-dimensional) feature vector. The huge advances enjoyed by many…
New task AQA tackles acoustic reasoning from sound scenes.
problem Promote research in acoustic reasoning.
method Generate acoustic scenes from elementary sounds and formulate questions.
result Preliminary results with models FiLM and MAC show promise.
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.
Paper aims to find joint representation between vocal tract geometry and speech sound acoustics.
problem Finding a joint latent representation between articulatory and acoustic domains for vowel sounds.
method Invertible neural network models, convolutional autoencoder, normalizing flows, semi-supervised learning.
result Satisfactory performance in articulatory-to-acoustic and acoustic-to-articulatory mapping.
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%.
Bayesian SHMM discovers acoustic units from unlabeled speech.
problem Discovering language-specific acoustic units from unlabeled speech.
method Bayesian Subspace Hidden Markov Model (SHMM) trained on labeled data to find new acoustic units on target language.
result Significantly outperforms previous HMM-based systems and compares favorably with Variational Auto Encoder-HMM.
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.
Paper proposes cost-sensitive detection for environmental acoustic sensing.
problem Infeasibility of manual analysis for large-scale acoustic data.
method Cost-sensitive classification with variational autoencoders in Neyman-Pearson framework.
result Improved control over false positive and false negative rates.
We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in …
ConvNet classifies whale vocalizations and ambient noise in acoustic recordings.
problem Automated detection and classification of marine mammal vocalizations in acoustic recordings.
method Convolutional Neural Network with a novel acoustic representation.
result Classifier accurately detects and classifies whale vocalizations and ambient noise.
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.
Improved acoustic word embeddings using shared decoder in multi-view encoders.
problem Learning discriminative acoustic word embeddings from text labels.
method Combining Siamese multi-view encoders with a shared decoder network to maximize the relationship between acoustic and text embeddings.
result 11.1% relative improvement in average precision on acoustic word discrimination task with WSJ dataset.
CLEAR dataset for acoustic reasoning tasks.
problem Acoustic reasoning and question answering.
method Data generation from elementary sounds, functional programs for question composition.
result Validation of current state-of-the-art visual Q&A models on AQA task.
Self-supervised method detects replay spoofing using acoustic configurations.
problem Challenges in collecting large-scale datasets for replay spoofing detection.
method Self-supervised pretraining of acoustic configurations using existing datasets.
result The method outperforms baseline by 30% on ASVspoof 2019 physical access dataset.
Method converts facial expressions and voice of a source speaker into a target speaker.
problem Separate conversion of facial and acoustic features leads to unnatural results.
method Uses three neural networks: conversion, waveform generation, and image reconstruction.
result Significantly higher naturalness achieved when converting both features together.
This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its potential, this model is employed to evaluate the performance of a large set of acoustic events detection systems. This model allows us to expli…
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
problem Mapping speech and text to fixed dimensions for phonetic confusability.
method Adapting SNE to sequential inputs, training two encoder neural networks.
result More accurate results with low-dimensional embeddings in word recognition tasks.
This work learns shared word embeddings for acoustic and phonetic sequences.
problem Mapping variable-length acoustic and phonetic sequences to fixed-dimensional vectors.
method Weak supervision and binary classification task to predict word similarity.
result Best model achieves an F1 score of 0.95 for binary classification.
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.
We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with Time Convolution (TC), followed by a Bidirectional Long Short-Term Memory (BLSTM), and a fi…
This paper improves speech recognition by using raw waveform signals in multi-span CNN acoustic models.
problem Improving speech recognition accuracy using raw waveform signals.
method Proposes a novel multi-span structure for acoustic modelling based on raw waveform signals with multiple CNN input layers.
result Multi-span acoustic models yield a lower word error rate (WER) than traditional FBANK feature-based models.
Improved hybrid acoustic model using interleaved self-attention and convolution.
problem Limited application of transformer in hybrid acoustic models.
method Proposed a model structure with interleaved self-attention and 1D convolution.
result Competitive recognition results on Librispeech dataset.
Proposes deep learning method for GCI detection from pathological speech.
problem Detecting glottal closure instants (GCI) in pathological acoustic speech.
method Convolutional neural network with fused deep acoustic speech and linear prediction residual features.
result Significantly better than state-of-the-art methods in GCI detection.
Three LF training criteria improve neural network acoustic models without cross-entropy pre-training.
problem Improving purely sequence-trained neural network acoustic models.
method Comparison of three lattice-free discriminative training criteria (MMI, bMMI, sMBR) on LVCSR tasks.
result LF-bMMI models outperform plain LF-MMI models by 5% WER on Switchboard datasets.
Enhances sound texture in CNN for better acoustic scene classification.
problem Limited understanding of how CNNs perceive audio scenes.
method Used Class Activation Mapping (CAM) to analyze log-Mel features and proposed edge enhancement using DoG and Sobel operators.
result Edge-enhanced log-Mel features improve CNN performance in acoustic scene classification.
Paper proposes a voting method to improve acoustic scene classification.
problem Improving acoustic scene classification accuracy.
method Punishment voting algorithm based on super categories construction.
result Punishment voting significantly improves classification performance.
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.
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic m…
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN…
Improved acoustic modeling with attentive adversarial learning.
problem Domain variability in acoustic modeling.
method Proposes an attentive ADIT method with an attention mechanism to improve domain-invariance of deep features.
result Improves deep feature domain-invariance and senone-discriminativity over ADIT.
U-Net trained to recover acoustic interference striations from distorted data.
problem Recovering acoustic interference striations from distorted signals.
method Training a U-Net using a random mode-coupling matrix model to generate training data.
result U-Net successfully recovers AISs under various conditions.
An improved algorithm for acoustic model parameter estimation.
problem Acoustic physical model parameter estimation for sound design.
method Multi-stage algorithm with deep learning, heuristics, and stochastic optimization.
result Optimization method refines deep learning estimates and improves objective metrics.
Review of acoustic scene classification methods in a competition.
problem Categorizing audio sequences into classes based on spectral content.
method Competition involving students and external participants, ablation study, neural network baseline comparison.
result Improved classification over neural network baseline.
Meta-learning improves few-shot acoustic event detection.
problem Detecting new audio events with limited labeled data.
method Formulated few-shot AED problem; explored supervised and meta-learning approaches.
result Meta-learning achieves superior performance in few-shot AED.
A simple fusion of deep and shallow learning improves acoustic scene classification.
problem Improving acoustic scene classification accuracy.
method Combining a deep learning approach and a feature engineering approach using a late fusion strategy.
result The fused system achieves 72.8% classification accuracy, outperforming individual methods.
Improved ASR for English-isiZulu code-switched speech with semi-supervised training.
problem Improving ASR for code-switched speech between English and isiZulu.
method Semi-supervised training using automatic transcription of multilingual speech data.
result Semi-supervised training achieved significant WER reduction in ASR performance.
New method uses overcomplete frames for better acoustic scene analysis.
problem Improving acoustic scene analysis in real-world applications.
method Risk minimization-based overcomplete frame thresholding.
result Validated on bird activity detection task using wavelets.
Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of such computational modules for extracting invariant and discriminativ…
Improved multi-modal emotion recognition using deep learning.
problem Combining acoustic and text modalities for emotion recognition.
method Proposes a deep learning-based approach to fuse text and acoustic data using SincNet for acoustic features and parallel DCNN and Bi-RNN branches for text processing with cross attention.
result Achieves 3.5% improvement in weighted accuracy compared to existing methods.
A new batch optimisation framework using Natural Gradient improves DNN acoustic models.
problem Optimizing DNN acoustic models for better word error rate approximation.
method Proposes a Natural Gradient (NG) approach to sequence training, correcting the gradient based on local curvature of KL-divergence.
result The NG method converges more quickly and can be applied to any sequence discriminative training criterion.
Deep learning outperforms classic machine learning in DAS event detection.
problem Event detection in Distributed Acoustic Sensing (DAS).
method Comparison of classic machine learning and image-based deep learning approaches.
result Image-based deep learning offers significantly faster event detection and execution times.
Jointly reduces echo, reverberation, and noise using neural networks.
problem Simultaneous reduction of acoustic echo, reverberation, and noise.
method Multichannel Gaussian modeling and neural network for joint optimization of filters.
result Outperforms individual and joint non-spectral models.
System builds Somali ASR for UN humanitarian efforts.
problem Developing ASR for under-resourced Somali language.
method Acoustic model training with annotated speech, neural architectures, language model data augmentation, acoustic data perturbation.
result Best system achieved 53.75% word error rate.
Paper tackles invariance of demodulation in shallow water acoustic communications.
problem Frequency-selective signal distortion (Doppler effect) in shallow water environments.
method Developed ML-based demodulation methods using DBN-NN and DBN-CNN.
result Demonstrated invariance of the proposed method to Doppler effect with 2dB error margin.
Report on acoustic model building from 1M hours of unlabeled speech.
problem Building acoustic models from large amounts of unlabeled speech data.
method Student/teacher training, scheduled learning, BMUF, gradient threshold compression SGD.
result Extremely large amounts of unlabeled data lead to significant relative WER improvements.