Interspeech 2010

772 papers

Top Research Directions

Research directions most represented by Interspeech 2010 papers.

Robust Natural Language Understanding for Noisy Speech Transcripts 29
Overcoming the Stationary Noise Assumption in Signal Enhancement 27
Generalization to Unseen Acoustic Environments 20
The Single Speaker Generalization Bottleneck in Speech Synthesis 20
Multi-Domain Feature Fusion for Robust Speech Analysis 18
Personalizing Speech Models with Minimal Data 17
Mitigating Performance Degradation in Noisy Speech Recognition 14
Statistical Comparison of Acoustic and Prosodic Features 13
Speaker Adaptation for Personalized Speech Recognition 13
Recovering Articulatory Movements from Speech Audio 12
Open Vocabulary Recognition for Spoken Language Systems 12
Overcoming Contextual Data Sparsity in Acoustic Modeling 12
Robust Pitch Estimation in Noisy Environments 11
Robust Voice Activity Detection in Noisy Environments 11
Generalizing from Limited Cohorts in Speech Research 11

Top Authors

AuthorPapers
Shrikanth Narayanan19
Haizhou Li16
EngSiong Chng5
Kong Aik Lee5
Lin-shan Lee5
Philip N. Garner5
Shinji Watanabe5
Bin Ma4
Dilek Hakkani Tur4
Dong Yu4
Eric Fosler-Lussier4
Florian Metze4
Yang Liu4
Zhen-Hua Ling4
Bhiksha Raj3
Gokhan Tur3
Kai Yu3
Nam Soo Kim3
Wei-Qiang Zhang3
Alfonso Ortega2

Impactful Papers

Papers from Interspeech 2010 that shaped research clusters.

Foundational

Influential

Papers

Title
HMM-based automatic visual speech segmentation using facial data
HMM-based prosodic structure model using rich linguistic context
HMM-based singing voice synthesis system using pitch-shifted pseudo training data
HMM-based text-to-articulatory-movement prediction and analysis of critical articulators
HMM based TTS for mixed language text
How abstract is phonetics?
How children acquire situation understanding skills?: a developmental analysis utilizing multimodal speech behavior corpus
Identification of abnormal audio events based on probabilistic novelty detection
Identifying articulatory goals from kinematic data using principal differential analysis
Impact of lack of acoustic feedback in EMG-based silent speech recognition
Impact of word classing on shrinkage-based language models
Improved generation of fundamental frequency in HMM-based speech synthesis using generation process model
Improved language recognition using mixture components statistics
Improved modelling of speech dynamics using non-linear formant trajectories for HMM-based speech synthesis
Improved neural network based language modelling and adaptation
Improved n-gram phonotactic models for language recognition
Improved phoneme recognition by integrating evidence from spectro-temporal and cepstral features
Improved real-time MRI of oral-velar coordination using a golden-ratio spiral view order
Improved spoken term detection by discriminative training of acoustic models based on user relevance feedback
Improved spoken term detection by feature space pseudo-relevance feedback
Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision
Improved training of excitation for HMM-based parametric speech synthesis
Improvement on plural unit selection and fusion
Improvements of search error risk minimization in viterbi beam search for speech recognition
Improvements to generalized discriminative feature transformation for speech recognition
Improvements to the equal-parameter BIC for speaker diarization
Improving ASR-based topic segmentation of TV programs with confidence measures and semantic relations
Improving ASR error detection with non-decoder based features
Improving back-off models with bag of words and hollow-grams
Improving cross database prediction of dialogue quality using mixture of experts
Improving Mandarin segmental duration prediction with automatically extracted syntax features
Improving monaural speaker identification by double-talk detection
Improving prosodic phrase prediction by unsupervised adaptation and syntactic features extraction
Improving speech synthesis of machine translation output
Improving the readability of class lecture ASR results using a confusion network
Incorporating MAP estimation and covariance transform for SVM based speaker recognition
Incorporating sparse representation phone identification features in automatic speech recognition using exponential families
Incremental acoustic valence recognition: an inter-corpus perspective on features, matching, and performance in a gating paradigm
Incremental composition of static decoding graphs with label pushing
Incremental diarization of telephone conversations
Incremental word learning using large-margin discriminative training and variance floor estimation
Influence of gestural salience on the interpretation of spoken requests
Influence of lexical tones on intonation in kammu
Influence of musical training on perception of L2 speech
Integrated feedback and noise reduction algorithm in digital hearing aids via oscillation detection
Integrate template matching and statistical modeling for speech recognition
Integrating MLP features and discriminative training in data sampling based ensemble acoustic modeling
Integration of cache-based model and topic dependent class model with soft clustering and soft voting
Integration of multilayer regression analysis with structure-based pronunciation assessment
Intelligibility predictions for speech against fluctuating masker

« prev Page 8/16 next »