Learning a better representation of speech soundwaves using restricted boltzmann machines

State of the art speech recognition systems rely on preprocessed speech features such as Mel cepstrum or linear predictive coding coefficients that collapse high dimensional speech sound waves into low dimensional encodings. While these have been successfully applied in speech recognition systems, such low dimensional encodings may lose some relevant information and express other information in a way that makes it difficult to use for discrimination. Higher dimensional encodings could both improve performance in recognition tasks, and also be applied to speech synthesis by better modeling the statistical structure of the sound waves. In this paper we present a novel approach for modeling speech sound waves using a Restricted Boltzmann machine (RBM) with a novel type of hidden variable and we report initial results demonstrating phoneme recognition performance better than the current state-of-the-art for methods based on Mel cepstrum coefficients.

• Publication year

  2011

• Venue

  IEEE International Conference on Acoustics, Speech, and Signal Processing

• Publication date

  2011-05-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.2011.5947700
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Practical Guide to Training Restricted Boltzmann Machines

  2012cited by this paper
• Information theory: A signal take on speech

  2010cited by this paper
• Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines

  2010cited by this paper
• Rectified Linear Units Improve Restricted Boltzmann Machines

  2010cited by this paper
• Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

  2010cited by this paper
• Deep Belief Networks for phone recognition

  2009influential reference
• Speech Recognition Using Augmented Conditional Random Fields

  2009influential reference
• CUDAMat: a CUDA-based matrix class for Python

  2009cited by this paper
• Unsupervised feature learning for audio classification using convolutional deep belief networks

  2009cited by this paper
• Use of Differential Cepstra as Acoustic Features in Hidden Trajectory Modeling for Phonetic Recognition

  2007influential reference
• Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition

  2006influential reference
• Efficient coding of natural sounds

  2002cited by this paper
• Training Products of Experts by Minimizing Contrastive Divergence

  2002cited by this paper
• Speech feature extraction using independent component analysis

  2000cited by this paper
• Improved phone recognition using Bayesian triphone models

  1998influential reference
• Heterogeneous measurements and multiple classifiers for speech recognition

  1998influential reference
• An information-maximization approach to blind separation and blind deconvolution

  1996cited by this paper
• An Information-Maximization Approach to Blind Separation and Blind Deconvolution

  1995cited by this paper
• An application of recurrent nets to phone probability estimation

  1994cited by this paper
• Information processing in dynamical systems: foundations of harmony theory

  1986cited by this paper

• Should Audio Front-Ends be Adaptive? Comparing Learnable and Adaptive Front-Ends

  2025cites this paper
• A Noise-Robust End-to-End Framework for Amharic Speech Recognition

  2025cites this paper
• Emotion Aware Speech Recognition System Using Deep Neural Networks

  2025cites this paper
• Enhanced speech emotion recognition using averaged valence arousal dominance mapping and deep neural networks

  2024cites this paper
• A hierarchical birdsong feature extraction architecture combining static and dynamic modeling

  2023cites this paper
• Evaluating raw waveforms with deep learning frameworks for speech emotion recognition

  2023cites this paper
• ЕND-TO-END SPEECH RECOGNITION SYSTEMS FOR AGGLUTINATIVE LANGUAGES

  2023cites this paper
• Multimodal Analysis of Acoustic and Linguistic Features in Entrepreneurial Pitches using Deep Learning

  2023influential citation
• Multiscale Audio Spectrogram Transformer for Efficient Audio Classification

  2023cites this paper
• Underwater Acoustic Target Recognition Combining Multi-scale Features and Attention Mechanism

  2023cites this paper
• SoundSynp: Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks

  2023cites this paper
• Application of virtual human sign language translation based on speech recognition

  2023cites this paper
• A survey on preprocessing and classification techniques for acoustic scene

  2023cites this paper
• DL 101: Basic introduction to deep learning with its application in biomedical related fields

  2022cites this paper
• Identifying the influence of transfer learning method in developing an end-to-end automatic speech recognition system with a low data level

  2022cites this paper
• Spoken Utterance Classification Task of Arabic Numerals and Selected Isolated Words

  2022cites this paper
• MRI-based radiomics analysis for differentiating phyllodes tumors of the breast from fibroadenomas

  2022cites this paper
• Depth-Adaptive Deep Neural Network Based on Learning Layer Relevance Weights

  2022cites this paper
• AST: Audio Spectrogram Transformer

  2021cites this paper
• Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation

  2021cites this paper
• Representation transfer learning from deep end-to-end speech recognition networks for the classification of health states from speech

  2021cites this paper
• Distribution-Invariant Deep Belief Network for Intelligent Fault Diagnosis of Machines Under New Working Conditions

  2021cites this paper
• LEAF: A Learnable Frontend for Audio Classification

  2021cites this paper
• Development of Hybrid Methods for Prediction of Principal Mineral Resources

  2021cites this paper
• Research on LSTM+Attention Model of Infant Cry Classification

  2021cites this paper
• REVIEW ON APPLICATION AREAS OF DEEP LEARNING

  2021cites this paper
• Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search

  2021cites this paper
• Paralinguistic Speech Processing: An Overview

  2021cites this paper
• Speech Representations and Phoneme Classification for Preserving the Endangered Language of Ladin

  2021cites this paper
• A Survey of Automatic Text Summarization: Progress, Process and Challenges

  2021cites this paper
• Acoustic monitoring using PyzoFlex®: a novel printed sensor for smart consumer products

  2021cites this paper
• Sequence-to-Sequence Acoustic-to-Phonetic Conversion Using Spectrograms and Deep Learning

  2021cites this paper
• Beyond Lp clipping: Equalization-based Psychoacoustic Attacks against ASRs

  2021cites this paper
• Synthesizing waveform sequence-to-sequence to augment training data for sequence-to-sequence speech recognition

  2021cites this paper
• Trace Transform Feature Learning for Offline Jawi Handwritten Recognition

  2021cites this paper
• Speech Recognition Using Enhanced Features with Deep Belief Network for Real Time Application

  2021cites this paper
• Learning Deep Representation of The Emotion Speech Signal

  2021cites this paper
• Machine Learning for Speaker Recognition

  2020cites this paper
• Deep learning-based clustering approaches for bioinformatics

  2020cites this paper
• Finding Quantum Critical Points with Neural-Network Quantum States

  2020cites this paper
• Development of integral model of speech recognition system for Uzbek language

  2020cites this paper
• Convergence of Markovian stochastic approximation for Markov random fields with hidden variables

  2020cites this paper
• Machine learning in quantum computers via general Boltzmann Machines: Generative and Discriminative training through annealing

  2020cites this paper
• Interval Type-2 Fuzzy Restricted Boltzmann Machine

  2020cites this paper
• Measuring the Impact of Accurate Feature Selection on the Performance of RBM in Comparison to State of the Art Machine Learning Algorithms

  2020cites this paper
• Speech Quality Classifier Model based on DBN that Considers Atmospheric Phenomena

  2020cites this paper
• Machine learning-based unenhanced CT texture analysis for predicting BAP1 mutation status of clear cell renal cell carcinomas

  2020cites this paper
• Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

  2020cites this paper
• SPEECH EMOTION RECOGNITION SURVEY

  2020cites this paper
• Hindi speech recognition using time delay neural network acoustic modeling with i-vector adaptation

  2020cites this paper
• Learning Restricted Boltzmann Machines with Sparse Latent Variables

  2020cites this paper
• A comprehensive survey and analysis of generative models in machine learning

  2020cites this paper
• A Review on Deep Learning Applications

  2020cites this paper
• Learning Restricted Boltzmann Machines with Few Latent Variables

  2020cites this paper
• A Speech Quality Classifier based on Tree-CNN Algorithm that Considers Network Degradations

  2020cites this paper
• Multi-task learning DNN to improve gender identification from speech leveraging age information of the speaker

  2020influential citation
• Deep Learning Models

  2020cites this paper
• Deep Learning Approaches for Speech Emotion Recognition

  2020cites this paper
• Intelligent Fault Diagnosis Method Based on Full 1-D Convolutional Generative Adversarial Network

  2020cites this paper
• Generative and discriminative training of Boltzmann machine through quantum annealing

  2020cites this paper
• End-to-End Speech Recognition in Agglutinative Languages

  2020cites this paper
• Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra

  2020cites this paper
• Raw Sign and Magnitude Spectra for Multi-Head Acoustic Modelling

  2020cites this paper
• On the Robustness and Training Dynamics of Raw Waveform Models

  2020cites this paper
• Deep Neural Baselines for Computational Paralinguistics

  2019cites this paper
• Massive computational acceleration by using neural networks to emulate mechanism-based biological models

  2019cites this paper
• Attention-Based Dense LSTM for Speech Emotion Recognition

  2019cites this paper
• Phonet: A Tool Based on Gated Recurrent Neural Networks to Extract Phonological Posteriors from Speech

  2019cites this paper
• End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition

  2019cites this paper
• Unsupervised Speech Representation Learning Using WaveNet Autoencoders

  2019cites this paper
• A Classical-Quantum Hybrid Approach for Unsupervised Probabilistic Machine Learning

  2019cites this paper
• Machine learning in ultrasound-guided spinal anesthesia

  2019cites this paper
• Deep Learning for Audio Signal Processing

  2019cites this paper
• Speech Recognition Using Deep Neural Networks: A Systematic Review

  2019cites this paper
• Deep Learning for Human Affect Recognition: Insights and New Developments

  2019cites this paper
• Learning representations of speech from the raw waveform. (Apprentissage de représentations de la parole à partir du signal brut)

  2019cites this paper
• Acoustic Model Adaptation from Raw Waveforms with Sincnet

  2019cites this paper
• Meta-Learning of Structured Representation by Proximal Mapping

  2019cites this paper
• 3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms

  2019cites this paper
• Keyword Spotting using Time-Domain Features in a Temporal Convolutional Network

  2019cites this paper
• Speech Emotion Classification Using Attention-Based LSTM

  2019cites this paper
• Unsupervised Representation Learning for Robust Speech Recognition

  2019cites this paper
• End-to-End Acoustic Modeling Using Convolutional Neural Networks

  2019cites this paper
• Distinctive Phonetic Features Modeling and Extraction Using Deep Neural Networks

  2019cites this paper
• Comparison and Analysis of SampleCNN Architectures for Audio Classification

  2019cites this paper
• Unsupervised Raw Waveform Representation Learning for ASR

  2019cites this paper
• ASM1D-GAN: An Intelligent Fault Diagnosis Method Based on Assembled 1D Convolutional Neural Network and Generative Adversarial Networks

  2019cites this paper
• A Speech Quality Classifier based on Signal Information that Considers Wired and Wireless Degradations

  2019cites this paper
• Sound Sharing and Retrieval

  2018cites this paper
• Noise Robust Automatic Speech Recognition Based on Spectro-Temporal Techniques

  2018cites this paper
• Deep Learning Methods for Underwater Target Feature Extraction and Recognition

  2018cites this paper
• Continual deep learning via progressive learning

  2018cites this paper
• Spam filtering using integrated distribution-based balancing approach and regularized deep neural networks

  2018cites this paper
• Multi-level region-of-interest CNNs for end to end speech recognition

  2018cites this paper
• An Ensemble Stacked Convolutional Neural Network Model for Environmental Event Sound Recognition

  2018cites this paper
• Learning filter widths of spectral decompositions with wavelets

  2018cites this paper
• Three-dimensional convolutional restricted Boltzmann machine for human behavior recognition from RGB-D video

  2018cites this paper
• Avaliação da Qualidade da Voz em Serviços de Comunicação usando Deep Learning

  2018cites this paper
• Voice Quality Assessment in Communication Services using Deep Learning

  2018cites this paper
• An evaluation of the performance of Restricted Boltzmann Machines as a model for anomaly network intrusion detection

  2018cites this paper