| ปี พ.ศ. 2556 |
| 1 |
Exploring Discourse-level Features for Audiobook-based Speech Synthesis |
| 2 |
Statistical Parametric Speech Synthesis Using Deep Neural Network |
| 3 |
Detecting Indirect Forms of Offensive Language using Commonsense Reasoning and Conceptual Modeling of Social Stereotypes |
| 4 |
Unsupervised learning for text-to-speech synthesis |
| 5 |
Predictability effects in language acquisition |
| 6 |
Intelligibility enhancement of synthetic speech in noise |
| ปี พ.ศ. 2555 |
| 7 |
Dynamic Bayesian Network-based Speech Synthesis |
| ปี พ.ศ. 2554 |
| 8 |
The Romanian Speech Synthesis (RSS) corpus: building a high quality HMM-based speech synthesis system using a high sampling rate |
| 9 |
Vocal Attractiveness Of Statistical Speech Synthesisers |
| 10 |
HMM-based Speech Synthesis from Audio Book Data |
| 11 |
Cross-lingual automatic speech recognition using tandem features |
| ปี พ.ศ. 2553 |
| 12 |
Towards the Development of a Web-based Alignment Platform |
| 13 |
An Interpolated Accent Map for Scotland |
| 14 |
Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project |
| 15 |
Synthesis of Child Speech With HMM Adaptation and Voice Conversion |
| 16 |
Thousands of Voices for HMM-Based Speech Synthesis-Analysis and Application of TTS Systems Built on Various ASR Corpora |
| 17 |
Thousands of Voices for HMM-Based Speech Synthesis-Analysis and Application of TTS Systems Built on Various ASR Corpora |
| 18 |
Out-of-vocabulary spoken term detection |
| 19 |
Stochastic Pronunciation Modelling for Out-of-Vocabulary Spoken Term Detection |
| 20 |
Synthesis of Child Speech with HMM Adaptation and Voice Conversion |
| 21 |
Letter-based speech synthesis |
| 22 |
Augmented set of features for confidence estimation in spoken term detection |
| 23 |
Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project |
| 24 |
Simple methods for improving speaker-similarity of HMM-based speech synthesis |
| 25 |
Thousands of Voices for HMM-based Speech Synthesis - Analysis and Application of TTS Systems Built on Various ASR Corpora |
| 26 |
Roles of the Average Voice in Speaker-adaptive HMM-based Speech Synthesis |
| 27 |
Personalising speech-to-speech translation in the EMIME project |
| 28 |
The role of higher-level linguistic features in HMM-based speech synthesis |
| 29 |
A classifier-based target cost for unit selection speech synthesis trained on perceptual data |
| 30 |
Unsupervised Cross-lingual Speaker Adaptation for HMM-based Speech Synthesis |
| 31 |
Identifying prosodic prominence patterns for English text-to-speech synthesis |
| 32 |
Roles of the Average Voice in Speaker-adaptive HMM-based Speech Synthesis |
| 33 |
Full Covariance Modelling for Speech Recognition |
| ปี พ.ศ. 2552 |
| 34 |
Speech Synthesis Without a Phone Inventory |
| 35 |
Posterior-based confidence measures for spoken term detection |
| 36 |
Stochastic Pronunciation Modelling for Spoken Term Detection |
| 37 |
HMM Adaptation and Voice Conversion for the Synthesis of Child Speech: A Comparison |
| 38 |
A Posterior Probability-based System Hybridisation and Combination for Spoken Term Detection |
| 39 |
Measuring the gap between HMM-based ASR and TTS |
| 40 |
Analysis of Unsupervised and Noise-Robust Speaker-Adaptive HMM-Based Speech Synthesis Systems toward a Unified ASR and TTS Framework |
| 41 |
Robust Speaker-Adaptive HMM-based Text-to-Speech Synthesis |
| 42 |
Term-Dependent Confidence for Out-of-Vocabulary Term Detection |
| 43 |
Speaker normalisation for large vocabulary multiparty conversational speech recognition |
| 44 |
Lexical influences on disfluency production |
| ปี พ.ศ. 2551 |
| 45 |
Automatic determination of sub-word units for automatic speech recognition |
| 46 |
HMM-based synthesis of child speech |
| 47 |
Robustness of HMM-based Speech Synthesis |
| 48 |
Covariance Updates for Discriminative Training by Constrained Line Search |
| 49 |
Unsupervised adaptation for HMM-based speech synthesis |
| 50 |
Single Speaker Segmentation and Inventory Selection Using Dynamic Time Warping Self Organization and Joint Multigram Mapping |
| 51 |
The Blizzard Challenge 2008 |
| 52 |
A comparison of grapheme and phoneme-based units for Spanish spoken term detection |
| 53 |
A comparison of phone and grapheme-based spoken term detection |
| 54 |
Cross-lingual Portability of MLP-Based Tandem Features -- A Case Study for English and Hungarian |
| 55 |
A Shrinkage Estimator for Speech Recognition with Full Covariance HMMs |
| 56 |
Generacion de una voz sintetica en Castellano basada en HSMM para la Evaluacion Albayzin 2008: conversion texto a voz |
| 57 |
Growing bottleneck features for tandem ASR |
| 58 |
A Posterior Approach for Microphone Array Based Speech Recognition |
| 59 |
Investigating Festival's target cost function using perceptual experiments |
| ปี พ.ศ. 2550 |
| 60 |
Articulatory feature recognition using dynamic Bayesian networks. |
| 61 |
Modelling prominence and emphasis improves unit-selection synthesis |
| 62 |
Sparse gaussian graphical models for speech recognition. |
| 63 |
Articulatory feature classifiers trained on 2000 hours of telephone speech |
| 64 |
Manual transcription of conversational speech at the articulatory feature level |
| 65 |
Articulatory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU Summer Workshop. |
| 66 |
Speech production knowledge in automatic speech recognition |
| 67 |
Factoring Gaussian Precision Matrices for Linear Dynamic Models |
| 68 |
Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPs |
| 69 |
Improved Average-Voice-based Speech Synthesis Using Gender-Mixed Modeling and a Parameter Generation Algorithm Considering GV |
| ปี พ.ศ. 2549 |
| 70 |
Speech recognition using linear dynamic models. |
| 71 |
Precise Estimation of Vocal Tract and Voice Source Characteristics |
| 72 |
Speech recognition using linear dynamic models. |
| 73 |
Towards Formal Structural Representation of Spoken Language: An Evolving Transformation System (ETS) Approach |
| ปี พ.ศ. 2548 |
| 74 |
Multisyn voices from ARCTIC data for the Blizzard challenge. |
| 75 |
Multidimensional scaling of listener responses to synthetic speech |
| 76 |
A hybrid ANN/DBN approach to articulatory feature recognition |
| 77 |
Inductive String Template-Based Learning of Spoken Language |
| 78 |
Detection of Symbolic Gestural Events in Articulatory Data for Use in Structural Representations of Continuous Speech |
| 79 |
Svitchboard 1: Small vocabulary tasks from switchboard 1 |
| 80 |
Subjective Evaluation of Join Cost and Smoothing Methods for Unit Selection Speech Synthesis |
| 81 |
Dae ye ken me ? Speech synthesis in the Gorbals region of Glasgow |
| ปี พ.ศ. 2547 |
| 82 |
Source-Filter Separation for Articulation-to-Speech Synthesis |
| 83 |
Estimating Detailed Spectral Envelopes Using Articulatory Clustering |
| 84 |
Subjective Evaluation of Join Cost Functions used in Unit Selection Speech Synthesis |
| 85 |
Phone Classification in Pseudo-Euclidean Vector Spaces |
| 86 |
Articulatory Feature Recognition Using Dynamic Bayesian Networks |
| 87 |
Structural Representation of Speech for Phonetic Classification |
| 88 |
Asynchronous Articulatory Feature Recognition Using Dynamic Bayesian networks |
| 89 |
Subjective Evaluation of Join Cost and Smoothing Methods |
| 90 |
Accurate Spectral Envelope Estimation for Articulation-to-Speech Synthesis |
| 91 |
Festival 2 – Build Your Own General Purpose Unit Selection Speech Synthesiser |
| 92 |
Linear dynamic models for automatic speech recognition |
| 93 |
Join Cost for Unit Selection Speech Synthesis |
| ปี พ.ศ. 2546 |
| 94 |
Estimating the Spectral Envelope of Voiced Speech Using Multi-Frame Analysis |
| 95 |
Transforming F0 Contours |
| 96 |
Named Entity Extraction from Word Lattices |
| 97 |
Discriminative Methods for Improving Named Entity Extraction on Speech Data |
| 98 |
Estimation of Voice Source and Vocal Tract Characteristics Based on Multi-Frame Analysis |
| 99 |
Transforming Voice Quality |
| 100 |
An accent-independent lexicon for automatic speech recognition. |
| 101 |
Dependence and independence in automatic speech recognition and synthesis. |
| 102 |
Modelling the uncertainty in recovering articulation from acoustics |
| 103 |
Kalman-Filter Based Join Cost for Unit-Selection Speech Synthesis |
| ปี พ.ศ. 2545 |
| 104 |
Framewise phone classification using support vector machines |
| 105 |
New objective distance measures for spectral discontinuities in concatenative speech synthesis |
| ปี พ.ศ. 2544 |
| 106 |
ASR - Articulatory Speech Recognition |
| 107 |
Speech recognition in the articulatory domain: investigating an alternative to acoustic HMMs |
| ปี พ.ศ. 2543 |
| 108 |
Speech recognition via phonetically-featured syllables |
| 109 |
An Automatic Speech Recognition System Using Neural Networks and Linear Dynamic Models to Recover and Model Articulatory Traces |
| 110 |
Detection of Phonological Features in Continuous Speech using Neural Networks |
| ปี พ.ศ. 2542 |
| 111 |
Dynamical system modelling of articulator movement. |
| ปี พ.ศ. 2541 |
| 112 |
Speech Recognition Via Phonetically Featured Syllables |
| 113 |
Intonation and dialogue context as constraints for speech recognition |
| ปี พ.ศ. 2540 |
| 114 |
Using intonation to constrain language models in speech recognition. |
| 115 |
Speech synthesis using non-uniform units in the Verbmobil project. |
| 116 |
Final Report for Verbmobil 1 TP 4.4 |
| ปี พ.ศ. 2539 |
| 117 |
Using Prosodic Information to Constrain Language Models for Spoken Dialogue |
