Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal

A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News

Bayesian Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification

Integrated and Enhanced Pipeline System to Support Spoken Language Analytics for Screening Neurocognitive Disorders

Natural Language-Assisted Sign Language Recognition

On the Audio-visual Synchronization for Lip-to-Speech Synthesis

wav2vec 2.0 ASR for Cantonese-Speaking Older Adults in a Clinical Setting

C²SLR: Consistency-enhanced Continuous Sign Language Recognition

C²SLR: Consistency-enhanced Continuous Sign Language Recognition

Local Context-aware Self-attention for Continuous Sign Language Recognition

Synthesizing Near Native-accented Speech for a Non-native Speaker by Imitating the Pronunciation and Prosody of a Native Speaker

Two-Stream Network for Sign Language Recognition and Translation

A Comparative Study of Acoustic and Linguistic Features Classification for Alzheimer’s Disease Detection

Non-Parallel Many-To-Many Voice Conversion by Knowledge Transfer from a Text-To-Speech Model

On-the-fly Data Augmentation for Text-to-speech Style Transfer

Multi-lingual multi-speaker text-to-speech synthesis for voice cloning with online speaker enrollment

Orthogonal Training for Text-independent Speaker Verification

Orthogonality Regularizations for End-to-End Speaker Verification

Stochastic Fine-Grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition

Mixup Learning Strategies for Text-independent Speaker Verification

Recurrent Poisson process unit for speech recognition

Denoised Senone I-Vectors for Robust Speaker Verification

DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification

Domain adaptation of end-to-end speech recognition in low-resource settings

End-to-End Low-Resource Lip-Reading with Maxout CNN and LSTM

Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model

Learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation

Multi-Head Attention for End-to-End Neural Machine Translation

Self-attentive Speaker Embeddings for Text-independent Speaker Verification

Subspace Based Sequence Discriminative Training of LSTM Acoustic Models With Feed-forward Layers

WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition

An Investigation Into Learning Effective Speaker Subspaces for Robust Unsupervised DNN Adaptation

Derivation of Document Vectors from Adaptation of LSTM Language Model

Learning factorized transforms for unsupervised adaptation of LSTM-RNN acoustic models

Speeding Up Softmax Computations in DNN-Based Large Vocabulary Speech Recognition by Senone Weight Vector Selection

To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-order Feedback From Multiple Histories

Unsupervised Adaptation of Student DNNs Learned from Teacher RNNs for Improved ASR Performance

An Investigation of Adaptation Techniques for Building Acoustic Models for Hearing-impaired Children in a CAPT Application

Senone I-Vectors for Robust Speaker Verification

Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition

Distinct Triphone Acoustic Modeling Using Deep Neural Networks

Eigentrigraphemes for under-resourced languages

Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition

Joint sequence training of phone and grapheme acoustic model based on multi-task learning deep neural networks

Modeling Inter-cluster and Intra-cluster Discrimination Among Triphones

Subspace Gaussian Mixture Model with State-dependent Subspace Dimensions

Eigentriphones for Context-Dependent Acoustic Modeling

Distinct Triphone Modeling by Reference Model Weighting

Derivation of eigentriphones by weighted principal component analysis

Speaker-ensemble hidden Markov modeling for automatic speech recognition

Subspace high-density discrete hidden Markov model for automatic speech recognition

Transition Probabilities Are More Important Than We Once Thought

A Fully Automated Derivation of State-based Eigentriphones for Triphone Modeling with No Tied States Using Regularization

Eigentriphones: A basis for context-dependent acoustic modeling

Improving speech recognition by explicit modeling of phone deletions

Problems of modeling phone deletion in conversational speech for speech recognition

Subvector-quantized high-density discrete hidden Markov model and its re-estimation

The Use of Subvector Quantization and Discrete Densities for Fast GMM Computation for Speaker Verification

Maximum Penalized Likelihood Kernel Regression for Fast Adaptation

Automatic estimation of decoding parameters using large-margin iterative linear programming

Fast GMM Computation for Speaker Verification Using Scalar Quantization and Discrete Densities

Discriminative training by iterative linear programming optimization

Min-max Discriminative Training of Decoding Parameters Using Iterative Linear Programming

Robust speaker verification using short-time frequency with long-time window and fusion of multi-resolutions

Kernel eigenspace-based MLLR adaptation

A Model-based estimation of phonotactic language verification performance

A Model-based Estimation of Phonotactic Language Verification Performance

Boosting with anti-models for automatic language identification

Robustness of several kernel-based fast adaptation methods on noisy LVCSR

Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting

Joint optimization of the frequency-domain and time-domain transformations in deriving generalized static and dynamic MFCCs

Minimization of utterance verification error rate as a constrained optimization problem

A comparison of various adaptation methods for speaker verification with limited enrollment data

Automatic Audio Indexing and Audio Playback Speed Control as Tools for Language Learning

Fast speaker adaption via maximum penalized likelihood kernel regression

Improving reference speaker weighting adaptation by the use of maximum-likelihood reference speakers

Unsupervised speaker adaptation using reference speaker weighting

Kernel eigenvoice speaker adaptation

Passenger route guidance system for multi-modal transit networks

Pruning hidden Markov models with optimal brain surgeon

A comparative study of two kernel eigenspace-based speaker adaptation methods on large vocabulary continuous speech recognition

High-density discrete HMM with the use of scalar quantization indexing

Kernel Eigenspace-based MLLR adaptation using multiple regression classes

Various reference speakers determination methods for embedded kernel Eigenvoice speaker adaptation

An acoustic-phonetic and a model-theoretic analysis of subspace distribution clustering hidden Markov models

Discriminative auditory-based features for robust speech recognition

Discriminative feature transformation by guided discriminative training

Eigenvoice speaker adaptation via composite kernel PCA

Improving Eigenspace-based MLLR Adaptation by Kernel PCA

Speedup of Kernel Eigenvoice Speaker Adaptation by Embedded Kernel PCA

Study of various composite kernels for kernel eigenvoice speaker adaptation

Using kernel PCA to improve eigenvoice speaker adaptation

Discriminative training of auditory filters of different shapes for robust speech recognition

Joint Estimation of Thresholds in a Bi-threshold Verification Problem

PLASER: Pronunciation Learning via Automatic Speech Recognition

Pruning Transitions in a Hidden Markov Model with Optimal Brain Surgeon

A mathematical relationship between full-band and multiband mel-frequency cepstral coefficients

An alternative approach of finding competing hypotheses for better minimum classification error training

Discriminative auditory features for robust speech recognition

Knowledge-based Sense Pruning using the HowNet: An Alternative to Word Sense Disambiguation

Performance of Discriminatively Trained Auditory Features on Aurora2 and Aurora3

Direct training of subspace distribution clustering hidden Markov model

Subspace distribution clustering hidden Markov model

Development of an Asynchronous Multi-band System for Continuous Speech Recognition

Rapid Speaker Adaptation Using MLLR and Subspace Regression Classes

Asynchrony with re-trained transition probabilities improves performance in multi-band speech recognition

MAP Adaptation with Subspace Regression Classes and Tying

Optimization of sub-band weights using simulated noisy speech in multi-band speech recognition

Pruning of state-tying tree using Bayesian Information Criterion with multiple mixtures

Training of context-dependent subspace distribution clustering hidden Markov model

Training of subspace distribution clustering hidden Markov model

Combining ANNs to improve phone recognition

Stream derivation and clustering schemes for subspace distribution clustering HMM

Subspace distribution clustering for continuous observation density hidden Markov models

Phone clustering using the Bhattacharyya distance

The contribution of consonants versus vowels to word recognition in fluent speech

Tone recognition of isolated Cantonese syllables

A robust algorithm for word boundary detection in the presence of noise

An NN based tone classifier for Cantonese

A robust speech/non-speech detection algorithm using time and frequency-based features

Communication parameter tests and parallel back propagation algorithms on iPSC/2 hypercube multiprocessor

Denoised Senone I-Vectors for Robust Speaker Verification

Article

DNN-Based Score Calibration With Multitask Learning for Noise Robust Speaker Verification

Article

Domain adaptation of end-to-end speech recognition in low-resource settings

Conference paper

End-to-End Low-Resource Lip-Reading with Maxout CNN and LSTM

Conference paper

Fast Derivation of Cross-lingual Document Vectors from Self-attentive Neural Machine Translation Model

Conference paper

Learning Effective Factorized Hidden Layer Bases Using Student-Teacher Training for LSTM Acoustic Model Adaptation

Conference paper

Multi-Head Attention for End-to-End Neural Machine Translation

Conference paper

Self-attentive Speaker Embeddings for Text-independent Speaker Verification

Conference paper

Subspace Based Sequence Discriminative Training of LSTM Acoustic Models With Feed-forward Layers

Conference paper

WaveNet MH-SRU: Deep and Wide Multiple-history Simple Recurrent Unit for Speech Recognition

Conference paper

An Investigation Into Learning Effective Speaker Subspaces for Robust Unsupervised DNN Adaptation

Conference paper

Derivation of Document Vectors from Adaptation of LSTM Language Model

Conference paper

Learning factorized transforms for unsupervised adaptation of LSTM-RNN acoustic models

Conference paper

Speeding Up Softmax Computations in DNN-Based Large Vocabulary Speech Recognition by Senone Weight Vector Selection

Conference paper

To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-order Feedback From Multiple Histories

Conference paper

Unsupervised Adaptation of Student DNNs Learned from Teacher RNNs for Improved ASR Performance

Conference paper

An Investigation of Adaptation Techniques for Building Acoustic Models for Hearing-impaired Children in a CAPT Application

Conference paper

Senone I-Vectors for Robust Speaker Verification

Conference paper

Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition

Article

Distinct Triphone Acoustic Modeling Using Deep Neural Networks

Conference paper

Eigentrigraphemes for under-resourced languages

Article

Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition

Conference paper

Joint sequence training of phone and grapheme acoustic model based on multi-task learning deep neural networks

Conference paper

Modeling Inter-cluster and Intra-cluster Discrimination Among Triphones

Conference paper

Subspace Gaussian Mixture Model with State-dependent Subspace Dimensions

Conference paper

Eigentriphones for Context-Dependent Acoustic Modeling

Article

Distinct Triphone Modeling by Reference Model Weighting

Conference paper

Derivation of eigentriphones by weighted principal component analysis

Conference paper

Speaker-ensemble hidden Markov modeling for automatic speech recognition

Conference paper

Subspace high-density discrete hidden Markov model for automatic speech recognition

Conference paper

Transition Probabilities Are More Important Than We Once Thought

Conference paper

A Fully Automated Derivation of State-based Eigentriphones for Triphone Modeling with No Tied States Using Regularization

Conference paper

Eigentriphones: A basis for context-dependent acoustic modeling

Conference paper

Improving speech recognition by explicit modeling of phone deletions

Conference paper

Problems of modeling phone deletion in conversational speech for speech recognition

Conference paper

Subvector-quantized high-density discrete hidden Markov model and its re-estimation

Conference paper

The Use of Subvector Quantization and Discrete Densities for Fast GMM Computation for Speaker Verification

Conference paper

Maximum Penalized Likelihood Kernel Regression for Fast Adaptation

Article

Automatic estimation of decoding parameters using large-margin iterative linear programming

Conference paper

Fast GMM Computation for Speaker Verification Using Scalar Quantization and Discrete Densities

Conference paper

Discriminative training by iterative linear programming optimization

Conference paper

Min-max Discriminative Training of Decoding Parameters Using Iterative Linear Programming

Conference paper

Robust speaker verification using short-time frequency with long-time window and fusion of multi-resolutions

Conference paper

Kernel eigenspace-based MLLR adaptation

Article

A Model-based estimation of phonotactic language verification performance

Conference paper

A Model-based Estimation of Phonotactic Language Verification Performance

Conference paper

Boosting with anti-models for automatic language identification

Conference paper

Robustness of several kernel-based fast adaptation methods on noisy LVCSR

Conference paper

Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting

Article

Joint optimization of the frequency-domain and time-domain transformations in deriving generalized static and dynamic MFCCs

Article

Minimization of utterance verification error rate as a constrained optimization problem

Article

A comparison of various adaptation methods for speaker verification with limited enrollment data

Conference paper

Automatic Audio Indexing and Audio Playback Speed Control as Tools for Language Learning

Conference paper

Fast speaker adaption via maximum penalized likelihood kernel regression

Conference paper

Improving reference speaker weighting adaptation by the use of maximum-likelihood reference speakers

Conference paper

Unsupervised speaker adaptation using reference speaker weighting

Conference paper

Kernel eigenvoice speaker adaptation

Article

Passenger route guidance system for multi-modal transit networks

Article

Pruning hidden Markov models with optimal brain surgeon

Article

A comparative study of two kernel eigenspace-based speaker adaptation methods on large vocabulary continuous speech recognition

Conference paper

High-density discrete HMM with the use of scalar quantization indexing

Conference paper

Kernel Eigenspace-based MLLR adaptation using multiple regression classes

Conference paper

Various reference speakers determination methods for embedded kernel Eigenvoice speaker adaptation

Conference paper

An acoustic-phonetic and a model-theoretic analysis of subspace distribution clustering hidden Markov models

Article

Discriminative auditory-based features for robust speech recognition

Article

Discriminative feature transformation by guided discriminative training

Conference paper

Eigenvoice speaker adaptation via composite kernel PCA

Conference paper

Improving Eigenspace-based MLLR Adaptation by Kernel PCA

Conference paper

Speedup of Kernel Eigenvoice Speaker Adaptation by Embedded Kernel PCA

Conference paper

Study of various composite kernels for kernel eigenvoice speaker adaptation

Conference paper

Using kernel PCA to improve eigenvoice speaker adaptation

Conference paper

Discriminative training of auditory filters of different shapes for robust speech recognition

Conference paper

Joint Estimation of Thresholds in a Bi-threshold Verification Problem

Conference paper

PLASER: Pronunciation Learning via Automatic Speech Recognition

Conference paper

Pruning Transitions in a Hidden Markov Model with Optimal Brain Surgeon

Conference paper

A mathematical relationship between full-band and multiband mel-frequency cepstral coefficients

Article

An alternative approach of finding competing hypotheses for better minimum classification error training

Conference paper

Discriminative auditory features for robust speech recognition

Conference paper

Knowledge-based Sense Pruning using the HowNet: An Alternative to Word Sense Disambiguation

Conference paper

Performance of Discriminatively Trained Auditory Features on Aurora2 and Aurora3

Conference paper

Direct training of subspace distribution clustering hidden Markov model

Article

Subspace distribution clustering hidden Markov model

Article

Development of an Asynchronous Multi-band System for Continuous Speech Recognition

Conference paper

Rapid Speaker Adaptation Using MLLR and Subspace Regression Classes

Conference paper

Asynchrony with re-trained transition probabilities improves performance in multi-band speech recognition

Conference paper

MAP Adaptation with Subspace Regression Classes and Tying

Conference paper

Optimization of sub-band weights using simulated noisy speech in multi-band speech recognition

Conference paper

Pruning of state-tying tree using Bayesian Information Criterion with multiple mixtures

Conference paper

Training of context-dependent subspace distribution clustering hidden Markov model

Conference paper

Training of subspace distribution clustering hidden Markov model

Conference paper

Combining ANNs to improve phone recognition

Conference paper

Stream derivation and clustering schemes for subspace distribution clustering HMM

Conference paper

Subspace distribution clustering for continuous observation density hidden Markov models

Conference paper

Phone clustering using the Bhattacharyya distance

Conference paper

The contribution of consonants versus vowels to word recognition in fluent speech

Conference paper

Tone recognition of isolated Cantonese syllables

Article

A robust algorithm for word boundary detection in the presence of noise

Article

An NN based tone classifier for Cantonese

Conference paper

A robust speech/non-speech detection algorithm using time and frequency-based features

Conference paper

Communication parameter tests and parallel back propagation algorithms on iPSC/2 hypercube multiprocessor

Conference paper