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 …
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
48 results for “neural network acoustic models”
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.
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.
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…
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…
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.
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly co…
Acoustic Neighbor Embeddingseess.AS
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.
We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief…
Improved language identification accuracy through signal combination methods.
problem Enhancing speech recognition accuracy across multiple languages.
method Combining low-level acoustic signals with language-specific recognizer signals using lattice-based ensemble models and deep neural networks.
result Deep neural network model outperforms lattice-based ensemble model, reducing error rate from 5.5% to 4.3%.
Deep neural network learns robust acoustic models from speech waveforms.
problem Robustness in speech recognition systems using standard feature extraction techniques.
method Deep convolutional neural network with stochastic variational inference and cosine modulated filters.
result Superior performance compared to baseline waveform-based models and deep CNNs with FBANK features.
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.
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.
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.
Doppler Invariant Demodulation for Shallow Water Acoustic Communications Using Deep Belief Networkseess.SP
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.
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
problem Acoustic scenes are rich and redundant, making classification challenging.
method Spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network.
result The method outperforms a strong convolutional neural network baseline and sets new state-of-the-art performance.
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.
A lightweight network and NAS method improve ASC tasks.
problem Heavy computational burden in acoustic scene classification.
method Inspired by MobileNetV2, unidirectional convolutions; dynamic NAS with evolutionary algorithm.
result 90.3% F1-score on DCASE2018 task 5, 25% fewer FLOPs.
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training loss function. This paper offers an empirical investigation on which aspects of …
Glottal Closure Instants Detection From Pathological Acoustic Speech Signal Using Deep Learningcs.SD
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.
Speech Synthesis using EEGeess.AS
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.
Self-Teaching Networkseess.AS
Self-teaching networks improve deep neural networks' generalization.
problem Improving deep neural networks' generalization capacity.
method Generates soft supervision labels to train lower layers, using an auxiliary loss to mimic the output layer.
result Self-teaching network achieves consistent improvements and outperforms existing methods in speech recognition tasks.
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
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.
Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Modelseess.AS
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.
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.
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.
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.
Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not s…
Improved topic modeling captures temporal relationships in speech.
problem Lack of temporal information in LDA for speech analysis.
method Temporal Markov chain extension to LDA for acoustic unit discovery.
result Improved phone segmentation results compared to base LDA.
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.
This paper uses deep learning to classify different types of cracks from acoustic emission events.
problem Classifying different types of cracks from acoustic emission events.
method Combining deep neural networks with Bidirectional Long Short Term Memory and statistical analysis.
result Achieves 92% accuracy in classifying different types of cracks.
CNNs improve generalization to unseen audio devices with increased width, not depth.
problem CNNs are sensitive to specific audio recording devices in acoustic scene classification.
method Investigated the relationship between over-parameterization and generalization in CNNs for audio classification.
result Increasing width improves generalization to unseen devices without increasing the number of parameters.
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.
Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognitioncs.CL
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding. Sparse representation of the test posteriors using this dictionary enables proje…
Improved speech recognition with cumulative adaptation methods.
problem Robust speech recognition in varying environments and speakers.
method Used a bidirectional LSTM neural network and i-vectors for adaptation.
result Achieved 13% relative improvement in word error rate.
Paper detects adversarial speech inputs with high accuracy.
problem Adversarial attacks on ASR systems.
method Uncertainty quantification using neural networks.
result Detection accuracy of adversarial inputs over 0.99.
Improved deep CNNs for ASC by optimizing receptive field size.
problem Deep CNNs perform poorly in ASC compared to simpler models.
method Analyzed and adapted the receptive field of ResNet and DenseNet.
result State-of-the-art performance achieved with optimized receptive field.
NLE embeds labels for domain adaptation with neural networks.
problem Adapting deep neural networks with unpaired source and target domain data.
method Distill source-domain knowledge into l-vectors, soft targets for adaptation.
result 14.1% relative word error rate reduction over direct re-training.
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…
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 scene classification with factorized CNN.
problem Acoustic scene classification in varying environments.
method Large-margin factorized CNN with triplet loss.
result Improved performance and better generalization on unseen data.
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddingseess.AS
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.
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
problem Improving acoustic scene classification accuracy.
method Harmonic and percussive source separation, two-stream CNN architecture, bilinear pooling.
result Improved accuracy on DCASE 2019 sub task 1a dataset.
Stochastic seismic waveform inversion using generative adversarial networks as a geological priorphysics.geo-ph
We present an application of deep generative models in the context of partial-differential equation (PDE) constrained inverse problems. We combine a generative adversarial network (GAN) representing an a priori model that creates subsurface geological structures and their petrophysical properties, with the numerical so…
Classifies spherical objects filled with water or air using acoustic echoes and Form Function.
problem Automatic recognition of spherical objects based on acoustic echoes.
method Form Function analysis of wideband sonar data, fed into a Multilayer Perceptron (MLP) classifier.
result Performance of the MLP classifier compared to SVM, highlighting the effectiveness of Form Function.
Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid acoustic modeling scenario. Despite the rapid progress in this area, a number of challenges remain …