Singapore Institute of Technology
Browse

Ian McLoughlin

Professor (Engineering; Information and computing sciences)

Singapore

Professor Ian McLoughlin joined Singapore Institute of Technology in early 2020. Previously, he was a Professor and Head of the School of Computing at the Medway campus of the University of Kent from 2015-2019, and before that a professor at the University of Science and Technology of China NELSLIP lab from 2012-2015. Before moving to China he worked as an academic for 10 years at Nanyang Technological University, Singapore and spent 10 years in the electronics R&D industry in New Zealand and the UK. Professor McLoughlin became a Chartered Engineer in 1998 and a Fellow of the IET in 2013. He has over 250 papers, 5 books and 10 patents in the fields of speech & audio, wireless communications and embedded systems, and has steered numerous technical innovations to successful conclusions.

Publications

  • Improving GANs for Speech Enhancement
  • An End-to-End Multi-Standard OFDM Transceiver Architecture Using FPGA Partial Reconfiguration
  • Spectrally efficient emission mask shaping for OFDM cognitive radios
  • Effective Exploitation of Posterior Information for Attention-Based Speech Recognition
  • Continuous robust sound event classification using time-frequency features and deep learning
  • In-Ear Electrode EEG for Practical SSVEP BCI
  • A new variance-based approach for discriminative feature extraction in machine hearing classification using spectrogram features
  • Speech reconstruction using a deep partially supervised neural network.
  • A New Time–Frequency Attention Tensor Network for Language Identification
  • Source-Aware Context Network for Single-Channel Multi-Speaker Speech Separation
  • Fisher vector based CNN architecture for image classification
  • LID-Senones and Their Statistics for Language Identification
  • Listening and Grouping: An Online Autoregressive Approach for Monaural Speech Separation
  • Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning
  • End-to-end DNN-CNN classification for language identification
  • Bag-of-features models based on C-DNN network for acoustic scene classification
  • Beyond equal-length snippets: How long is sufficient to recognize an audio scene?
  • Spatio-temporal attention pooling for audio scene classification
  • What makes audio event detection harder than classification?
  • Enabling Early Audio Event Detection with Neural Networks
  • Deep neural network for robust speech recognition with auxiliary features from laser-Doppler vibrometer sensor
  • GFM-VOC: A real-time voice quality modification system
  • An attention pooling based representation learning method for speech emotion recognition
  • Acoustic modeling with densely connected residual network for multichannel speech recognition
  • Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks
  • A new time-frequency attention mechanism for TDNN and CNN-LSTM-TDNN, with application to language identification
  • A Region Based Attention Method for Weakly Supervised Sound Event Detection and Classification
  • An improved deep embedding learning method for short duration speaker verification
  • A training-based speech regeneration approach with cascading mapping models
  • An effective deep embedding learning architecture for speaker verification
  • Improving aggregation and loss function for better embedding learning in end-to-end speaker verification system
  • A robust framework for acoustic scene classification
  • Formant smoothing for quality improvement of post-laryngectomised speech reconstruction
  • A Spectral Glottal Flow Model for Source-filter Separation of Speech
  • A Conditional Generative Model for Speech Enhancement
  • Improved Conditional Generative Adversarial Net Classification for Spoken Language Recognition
  • On the mental fatigue analysis of SSVEP entrainment
  • Early detection of continuous and partial audio events using CNN
  • Glottal Flow Synthesis for Whisper-to-Speech Conversion
  • End-to-End Language Identification Using High-Order Utterance Representation with Bilinear Pooling
  • Improvements on Deep Bottleneck Network based I-Vector Representation for Spoken Language Identification
  • LID-senone Extraction via Deep Neural Networks for End-to-End Language Identification
  • Image classification with CNN-based Fisher vector coding
  • Robust Sound Event Detection in Continuous Audio Environments
  • Time–Frequency Feature Fusion for Noise Robust Audio Event Classification
  • Robust acoustic scene classification using a multi-spectrogram encoder-decoder framework
  • Variance Normalised Features for Language and Dialect Discrimination
  • Incandescent Bulb and LED Brake Lights: Novel Analysis of Reaction Times
  • CNN-MoE Based Framework for Classification of Respiratory Anomalies and Lung Disease Detection
  • Multi-Granularity Sequence Alignment Mapping for Encoder-Decoder Based End-to-End ASR
  • The Use of Low-Frequency Ultrasound for Voice Activity Detection
  • Mouth State Detection From Low-Frequency Ultrasonic Reflection
  • Super-audible Voice Activity Detection
  • Cross-layer TCP/IP Segmentation, Re-routing and Adaptive Modulation Techniques to Exploit Instantaneous BER Variations on Parallel Subchannels
  • Reconstruction of pitch for whisper-to-speech conversion of Chinese
  • Local Coding based Matching Kernel Method for Image Classification
  • Deep Bottleneck Features for Spoken Language Identification
  • Tone confusion in spoken and whispered Mandarin Chinese
  • Task-aware Deep Bottleneck Features for Spoken Language Identification
  • Shaping Spectral Leakage for IEEE 802.11p Vehicular Communications
  • A new mechanical index for gauging the human bio-effects of low frequency ultrasound
  • A Unified Framework for GPS Code and Carrier-Phase Multipath Mitigation Using Support Vector Regression
  • Speech Playback Geometry for Smart Homes
  • Whisper-to-speech conversion using restricted Boltzmann machine arrays
  • Square-Rich Fixed Point Polynomial Evaluation on FPGAs
  • Robust and Efficient OFDM Synchronisation for FPGA-Based Radios
  • Super-Audible Voice Activity Detection
  • Local coding based matching kernel method for image classification.
  • Deep bottleneck features for spoken language identification.
  • Mouth State Detection From Low-Frequency Ultrasonic Reflection
  • Classifying watermelon ripeness by analysing acoustic signals using mobile devices
  • Low frequency ultrasonic voice activity detection using convolutional neural networks
  • Deep bottleneck network based i-vector representation for language identification
  • The use of low-frequency ultrasound for voice activity detection
  • Task-aware deep bottleneck features for spoken language identification
  • Phonated speech reconstruction using twin mapping models
  • Robust sound event recognition using convolutional neural networks
  • Whisper-to-speech conversion using restricted Boltzmann machine arrays
  • Reconstruction of phonated speech from whispers using formant-derived plausible pitch modulation
  • Improved i-Vector Representation for Speaker Diarization
  • Learning compact structural representations for audio events using regressor banks
  • Efficient integer frequency offset estimation architecture for enhanced OFDM synchronization
  • Compact convolutional neural network transfer learning for small-scale image classification
  • Performance evaluation of deep bottleneck features for spoken language identification
  • A spectral based visual matching method for image classification
  • Comparative whisper vowel space for Singapore English and British English accents
  • Robust sound event classification using deep neural networks
  • Cross-layer TCP/IP segmentation, re-routing and adaptive modulation techniques to exploit instantaneous BER variations on parallel subchannels
  • Efficient Large Integer Squarers on FPGA
  • Reconstruction of pitch for whisper-to-speech conversion of Chinese
  • Shaping Spectral Leakage for IEEE 802.11p Vehicular Communications
  • Multi-task deep neural network acoustic models with model adaptation using discriminative speaker identity for whisper recognition
  • Efficient multi-standard cognitive radios on FPGAs
  • Tone confusion in spoken and whispered Mandarin Chinese
  • Speech and Audio Processing
  • Deep Bottleneck Feature for Image Classification
  • Improved language identification using deep bottleneck network
  • Square-rich fixed point polynomial evaluation on FPGAs
  • Robust and Efficient OFDM Synchronization for FPGA-Based Radios
  • Speech playback geometry for smart homes
  • Human Mouth State Detection Using Low Frequency Ultrasound
  • Computer Architecture: an embedded approach
  • MetroBuzz: Interactive 3D visualization of spatiotemporal data
  • Performance Analysis of Adaptive Modulation and Transmit Antenna Selection with Channel Prediction Errors and Feedback Delay
  • Bio-effects and safety of low-intensity, low-frequency ultrasonic exposure
  • Campus Mobility for the Future: The Electric Bicycle
  • Channel prediction in non-regenerative multi-antenna relay selection systems
  • Multi-touch Wall Displays for Informational and Interactive Collaborative Space
  • Mobile Communications Using Source-Selected Multi-Antenna AF Relays Over Dual-Hop Nakagami-m Channels
  • Method and apparatus for determining mouth state using low frequency ultrasonics
  • Message from WEISS-12 Workshop Chairs
  • Cross-layer MIMO-Links Exploiting Packet Re-routing Mechanisms and Adaptive Modulation in Diverse Channel Condition
  • TCP-based Multi Parallel Links Exploiting Packet Re-routing Mechanisms in Diverse Channel Condition
  • Fourier transform-based scalable image quality measure
  • Classifying watermelon ripeness by analysing acoustic signals using mobile devices
  • Reconstruction of continuous voiced speech from whispers
  • Efficient Squarer Design for FPGA Implementation
  • A Comprehensive Vowel Space for Whispered Speech
  • Exemplar Based Language Recognition Method For Short-Duration Speech Segments
  • Measuring resonances of the vocal tract using frequency sweeps at the lips
  • GPS multipath mitigation: a nonlinear regression approach
  • Packet Switching, AM Adjustment and Retry Mechanisms for Cross-Layer MIMO Link Design
  • A new mechanical index for gauging the human bioeffects of low frequency ultrasound.
  • Human mouth state detection using low frequency ultrasound
  • Modelling WSNS using OMNeT++
  • From whispers to normal speech: Offering natural voice to laryngectomees
  • Cross-layer MIMO-link exploiting packet re-routing mechanisms and adaptive modulation in diverse channel condition
  • TCP-based multi parallel links exploiting packet re-routing mechanisms in diverse channel condition
  • Reconstruction of continuous voiced speech from whispers
  • Multi-touch wall displays for informational and interactive collaborative space
  • Multi-touch wall displays for informational and interactive collaborative space
  • Performance analysis of adaptive modulation and transmit antenna selection with channel prediction errors and feedback delay
  • Open-Source and Consumer Electronics—The Back Door to World Domination: Why Reinvent the Wheel (Especially When Nice People are Giving Wheels Away for Free)?
  • Virtualized Development and Testing for Embedded Cluster Computing
  • Bio-effects and safety of low-intensity, low-frequency ultrasonic exposure
  • Message from WEISS-12 workshop chairs
  • Multi-touch wall displays for informational and interactive collaborative space
  • Mobile communications using source-selected multi-antenna AF relays over dual-hop nakagami- m channels
  • A comprehensive vowel space for whispered speech
  • Measuring resonances of the vocal tract using frequency sweeps at the lips
  • MetroBuzz: Interactive 3D visualization of spatiotemporal data
  • Channel prediction in non-regenerative multi-antenna relay selection systems
  • Fourier transform-based scalable image quality measure
  • GPS multipath mitigation: A nonlinear regression approach
  • Artificial phonation for patients suffering voice box lesions
  • Nonintrusive quality assessment of noise suppressed speech with Mel-filtered energies and support vector regression
  • TCP/IP link layer error mitigation for MIMO wireless links
  • Whisper vowel diagrams for Singapore English
  • Data collection, communications and processing in the Sumatran GPS array (SuGAr)
  • Low-power correlation for IEEE 802.16 OFDM synchronization on FPGA
  • An embedded systems graduate education for Singapore
  • Method,Apparatus and Computer Readable Medium for Fast Arithmetic in Digital Logic
  • Linear predictive analysis for ultrasonic speech
  • Applied Speech and Audio Processing
  • Autoregressive Modelling for Linear Prediction of Ultrasonic Speech
  • Data collection, communications and processing in the Sumatran GPS array (SuGAr)
  • Effects of Channel Prediction for Transmit Antenna Selection With Maximal-Ratio Combining in Rayleigh Fading
  • Development of Nano-satellite Space segment and Ground Station
  • Method and System for Reconstructing Speech from an Input Signal Comprising Whispers
  • Message from the honorary chair
  • Message from the APESER 2010 Program Chairs
  • Analysis-by-synthesis method for whisper-speech reconstruction
  • Dynamic scaling scheme for hardware-accelerated edge detection
  • Fast and accurate GCPS selection scheme for SAR image registration based on an improved Trajkovic corner detector
  • Joint audio video quality evaluation for distance or online education systems
  • Regeneration of Speech in Voice-Loss Patients
  • Applied speech and audio processing: With matlab ® examples
  • Vowel Intelligibility in Chinese
  • A group ring construction of the extended binary Golay code
  • Speech Recognition for Smart Homes
  • Fast and accurate GCPS selection scheme for SAR image registration based on an improved Trajkovic corner detector
  • Performance of Dual-Hop Multi-Antenna Systems with Fixed Gain Amplify-and-Forward Relay Selection
  • SLC SAR speckle filtering using homoskedastic features in logarithmic transformed domain
  • Spectral enhancement of whispered speech based on probability mass function
  • Effects of channel prediction for transmit antenna selection with maximal-ratio combining in Rayleigh fading
  • FMLE SAR speckle filter using the distance consistency property in homoskedasticlog-transformed domain
  • Virtualized development and testing of embedded computing clusters
  • A perspective on the experiential learning of computer architecture
  • Autoregressive modelling for linear prediction of ultrasonic speech
  • Linear predictive analysis for ultrasonic speech
  • Message from the APESER 2010 program chairs
  • Neural network-assisted reconstruction of full polarimetric SAR information
  • Point-to-point OMNeT++ based simulation of reliable transmission using realistic segmentation and reassembly with error control
  • Reconstruction of normal sounding speech for laryngectomy patients through a modified CELP codec
  • Reliability through redundant parallelism for micro-satellite computing
  • Voiced speech from whispers for post-laryngectomised patients
  • Speech rehabilitation methods for laryngectomised patients
  • Toward a comprehensive vowel space for whispered speech
  • Channel prediction for mitigating feedback link issues in transmit antenna selection systems
  • Non-intrusive speech quality assessment with support vector regression
  • Hardware-accelerated edge detection for polarimetric synthetic aperture radar data
  • Joint audio video quality evaluation for distance or online education systems
  • Keypress biometrics for user validation in mobile consumer devices
  • Secure embedded systems: The threat of reverse engineering
  • Analysis-by-synthesis method for whisper-speech reconstruction
  • Predictive receive-directed antenna selection for quasistatic Rayleigh fading channel
  • An embedded systems graduate education for Singapore
  • Linux as a teaching aid for embedded systems
  • Tone discrimination in Mandarin Chinese
  • Achieving low-cost high-reliability computation through redundant parallel processing
  • FPGA implementation of space-time block coding systems
  • Channel estimation complexity reduction using caching
  • First beowulf cluster in space
  • Centralised computation service architecture for the X-Sat micro-satellite
  • Design, testing and verification of a microsatellite on-board data processing unit using commercial grade processors
  • Error Detection and Correction for microsatellite software running on \ COTS\ processors
  • Achieving low-cost high-reliability computation through redundant parallel processing
  • Extension of proposal of standards for intelligibility tests of Chinese speech: CDRT-tone
  • Fault tolerance through redundant \ COTS\ components for satellite processing applications
  • A methodology for improving PESQ accuracy for Chinese speech
  • Method and Apparatus for Speech Enhancement in a Speech Communication System
  • Method and Apparatus for Fast Arithmetic in Digital Logic
  • How to track pitch pulses in LP residual? Joint time-frequency distribution approach
  • How to track pitch pulses? - Joint time-frequency distribution approach
  • Adaptive bit allocation for LSP parameter quantization
  • Fault-tolerant Computer for Low Earth Orbit Micro-satellites
  • Embedded Linux platform for a fault tolerant space based parallel computer
  • Evaluation of ITU-T G. 728 as a voice over IP codec for Chinese speech
  • Fault tolerant computer for low Earth orbit micro satellites
  • Low-cost space-borne processing on a reconfigurable parallel architecture
  • Link layer error mitigation in rural UHF-MIMO linking systems
  • Low Complexity Detection Algorithms For A MIMO-OFDM System
  • Intelligibility evaluation of GSM coder for Mandarin speech using CDRT
  • A scalable parallel computational core for embedded processing
  • A methodology for improving \ PESQ\ accuracy for \ C\ hinese speech
  • How to track pitch pulse in LP residual - Joint Time-Frequency Distribution Approach
  • A modular computational engine for communications processing
  • Intelligibility evaluation of GSM coder for Mandarin speech using CDRT
  • Joint Time- Frequency Distribution Analysis of Pitch Pulses
  • A reconfigurable platform for \ MIMO\ research - realtime implementation of a 4x4 adaptive multi-variate \ DFE\
  • Improvements Relating to Radio Communication Systems
  • Time reversal space time block coding with channel estimation errors
  • The 2k2: A modular computational toolkit for embedded signal processing
  • Fault tolerance through redundant COTS components for satellite processing applications
  • Channel estimation complexity reduction using caching
  • Transmit antenna selection for UHF MIMO linking
  • A methodology for improving PESQ accuracy for Chinese speech
  • A scalable parallel computational core for embedded processing
  • Perceptual audio data concealment and watermarking scheme using direct frequency domain substitution
  • Link layer error mitigation in rural UHF-MIMO linking systems
  • An FPGA-based MIMO and space-time processing platform
  • Performance investigation and implementation of a real-time adaptive MIMO-DFE system
  • The art of public speaking for engineers
  • FPGA implementation of space-time block coding systems
  • Fault tolerant computer for low earth orbit micro satellites
  • Low-cost space-borne processing on a reconfigurable parallel architecture
  • Extension of proposal of standards for intelligibility tests of Chinese speech: CDRT-tone
  • Intelligibility evaluation of GSM coder for Mandarin speech using CDRT
  • How to track pitch pulses in LP residual? - Joint Time-Frequency Distribution approach
  • Adaptive bit allocation for LSP parameter quantization
  • Speech recognition engine adaptions for smart home dialogues
  • LSP parameter interpretation for speech classification
  • Method and Apparatus for Speech Enhancement in a Speech Communications System
  • Adaptive bit allocation for LSP parameter quantization
  • Subjective Intelligibility Testing of Chinese Speech
  • Adaptive bit allocation for LSP\ parameter quantization
  • DSP software development
  • Mandarin speech coding using a modified RPE-LTP technique
  • Line spectral pairs
  • MP3 player on JUMPtec DIMM-PC/486-I
  • Data concealment in audio using a nonlinear frequency distribution of PRBS coded data and frequency-domain LSB insertion.
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • Hardware architecture for LSB data concealment using subband filterbank coding
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • Proposal of standards for intelligibility testing of Chinese Speech
  • Variable Rate Coding Techniques for Mandarin Speech over Packet Networks
  • Switched-basis LSP quantization
  • Mandarin speech coding using a modified RPE_LTP technique
  • Novel dynamic bit allocation method for LSP quantization
  • Proposal of standards for intelligibility tests of Chinese speech
  • Performance comparison of ICA neural networks separating audio signals
  • The implementation of a high accuracy optical measurement technique of particular interest to miniature optics
  • LSP-based speech modification for intelligibility enhancement
  • THE IMPLEMENTATION OF A HIGH-ACCURACY OPTICAL MEASUREMENT TECHNIQUE OF PARTICULAR INTEREST TO MINIATURE OPTICS
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • LSP analysis and processing for speech coders
  • LSP analysis and processing for speech coders
  • Data concealment in audio using a nonlinear frequency distribution of PRBS coded data and frequency-domain LSB insertion
  • High accuracy displacement measurements for integrated optical components
  • Analysis of adaptive modulation with antenna selection under channel prediction errors
  • Predictive Transmit Antenna Selection with Maximal Ratio Combining
  • Reverse engineering of embedded consumer electronic systems
  • LSP-based speech modification for intelligibility enhancement
  • Mandarin Speech Coding using a Modified RPE_LTP Technique
  • Novel dynamic bit allocation method for LSP quantization
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • The implementation of a high accuracy optical measurement technique of particular interest to miniature optics
  • Modelling WSNs Using OMNeT++
  • Hardware architecture for data concealment using sub-band coding, LSB coding and pseudo-random bit stream generators
  • Mandarin speech coding using a modified RPE_LTP technique
  • Novel dynamic bit allocation method for LSP quantization
  • Data concealment in audio using a nonlinear frequency distribution of PRBS coded data and frequency-domain LSB insertion
  • Proposal of standards for intelligibility tests of Chinese speech
  • LSP analysis and processing for speech coders
  • LSP-based speech modification for intelligibility enhancement
  • Packet Switching, AM Adjustment and Retry Mechanisms for Cross-Layer MIMO Link Design
  • Investigating the Cognitive Response of Brake Lights in Initiating Braking Action Using EEG
  • Cross-Lingual Self-training to Learn Multilingual Representation for Low-Resource Speech Recognition
  • DOMAIN ROBUST DEEP EMBEDDING LEARNING FOR SPEAKER RECOGNITION
  • Wearable and implantable medical devices A fantastic voyage
  • Tragus based vagus nerve stimulation for stress reduction
  • JOINT GENERATIVE-CONTRASTIVE REPRESENTATION LEARNING FOR ANOMALOUS SOUND DETECTION
  • SELF-SUPERVISED REPRESENTATION LEARNING FOR UNSUPERVISED ANOMALOUS SOUND DETECTION UNDER DOMAIN SHIFT
  • Extremely low footprint end-to-end ASR system for smart device
  • An effective speaker recognition method based on joint identification and verification supervisions
  • Non-Verbal Auditory Aspects of Human-Service Robot Interaction
  • FRONTEND ATTRIBUTES DISENTANGLEMENT FOR SPEECH EMOTION RECOGNITION
  • Acoustic Based Footstep Detection in Pervasive Healthcare
  • On the potential of transauricular electrical stimulation to reduce visually induced motion sickness
  • Automated Assessment of Glottal Dysfunction Through Unified Acoustic Voice Analysis
  • Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
  • An Ensemble of Deep Learning Frameworks for Predicting Respiratory Anomalies
  • Auditory evoked potential detection during pure-tone audiometry
  • Multi-view audio and music classification
  • On the potential of transcutaneous auricular vagus nerve stimulation to reduce visually induced motion sickness
  • An effective deep embedding learning method based on dense-residual networks for speaker verification
  • Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
  • AST-SED: AN EFFECTIVE SOUND EVENT DETECTION METHOD BASED ON AUDIO SPECTROGRAM TRANSFORMER
  • Inception-Based Network and Multi-Spectrogram Ensemble Applied to Predict Respiratory Anomalies and Lung Diseases
  • Vibro-motor Reprocessing Therapy towards Managing Motion Sickness Reduction: Evidence from EEG
  • An effective perturbation based semi-supervised learning method for sound event detection
  • Motion sickness reduction through vibro-motor reprocessing therapy: A first study
  • Automatic assessment of dysarthric severity level using audio-video cross-modal approach in deep learning
  • Auricular Vagus Nerve Stimulation for Stress Reduction: Evidence from Alpha Prefrontal Asymmetry
  • Multi-view audio and music classification
  • A weight moving average based alternate decoupled learning algorithm for long-tailed language identification
  • Robust Prototype Learning for Anomalous Sound Detection
  • Fine-tuning Audio Spectrogram Transformer with Task-aware Adapters for Sound Event Detection
  • D-MONA: A dilated mixed-order non-local attention network for speaker and language recognition
  • An effective mutual mean teaching based domain adaptation method for sound event detection
  • An improved mean teacher based method for large scale weakly labeled semi-supervised sound event detection
  • Class-Aware Distribution Alignment based Unsupervised Domain Adaptation for Speaker Verification
  • An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies
  • Self-attention generative adversarial network for speech enhancement
  • A Light-weight Deep Learning Model for Remote Sensing Image Classification
  • An Online Speaker-aware Speech Separation Approach Based on Time-domain Representation
  • Extremely low footprint end-to-end ASR system for smart device
  • On the Use of a Spectral Glottal Model for the Source-filter Separation of Speech
  • Enabling early audio event detection with neural networks
  • Semi-supervised end-to-end ASR via teacher-student learning with conditional posterior distribution
  • Incandescent bulb and LED brake lights: Novel analysis of reaction times
  • Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection
  • Inception-based network and multi-spectrogram ensemble applied for predicting respiratory anomalies and lung diseases
  • On multitask loss function for audio event detection and localization
  • Robust Deep Learning Framework for Predicting Respiratory Anomalies and Diseases
  • Improving GANs for speech enhancement
  • Self-attention generative adversarial network for speech enhancement
  • SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition
  • Triplet-Center Loss Based Deep Embedding Learning Method for Speaker Verification
  • Robust deep learning framework for predicting respiratory anomalies and diseases
  • Towards more accurate automatic sleep staging via deep transfer learning
  • Unifying isolated and overlapping audio event detection with multi-label multi-task convolutional recurrent neural networks
  • SAN-M: Memory equipped self-attention for end-to-end speech recognition
  • Deep Feature Embedding and Hierarchical Classification for Audio Scene Classification
  • Deep feature embedding and hierarchical classification for audio scene classification
  • CNN-MoE based framework for classification of respiratory anomalies and lung disease detection
  • LSTM-TDNN WITH CONVOLUTIONAL FRONT-END FOR DIALECT IDENTIFICATION IN THE 2019 MULTI-GENRE BROADCAST CHALLENGE
  • A Framework for Understanding the Weaponisation of the Internet

Usage metrics

Co-workers & collaborators

Ian McLoughlin's public data