INTERSPEECH 2010

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed INTERSPEECH-2010 Paper

click to vote

INTERSPEECH
2010

86views Signal Processing» more INTERSPEECH 2010»

Excitation modeling based on waveform interpolation for HMM-based speech synthesis

1 years 4 days ago

Download hi.snu.ac.kr

It is generally known that a well-designed excitation produces high quality signals in hidden Markov model (HMM)-based speech synthesis systems. This paper proposes a novel techni...

June Sig Sung, Doo Hwa Hong, Kyung Hwan Oh, Nam So...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	86	Excitation modeling based on waveform interpolation for HMM-based speech synthesis	claim
2	78	Adaptation of a tongue shape model by local feature transformations	claim
3	72	Recurrent neural network based language model	claim
4	68	SAFE: a statistical algorithm for F0 estimation for both clean and noisy speech	claim
5	67	Speech dominoes and phonetic convergence	claim
6	65	Probabilistic integration of joint density model and speaker model for voice conversion	claim
7	63	Towards a robust face recognition system using compressive sensing	claim
8	61	Deep-structured hidden conditional random fields for phonetic recognition	claim
9	59	Still talking to machines (cognitively speaking)	claim
10	59	Revisiting VTLN using linear transformation on conventional MFCC	claim
11	58	On-the-fly lattice rescoring for real-time automatic speech recognition	claim
12	56	An implementation of decision tree-based context clustering on graphics processing units	claim
13	56	Identifying articulatory goals from kinematic data using principal differential analysis	claim
14	55	Extractive summarization using a latent variable model	claim
15	55	Memory-based active learning for French broadcast news	claim
16	55	Kinematic analysis of tongue movement control in spastic dysarthria	claim
17	54	Channel detectors for system fusion in the context of NIST LRE 2009	claim
18	54	What else is new than the hamming window? robust MFCCs for speaker recognition via multitapering	claim
19	53	Bayesian speaker recognition using Gaussian mixture model and laplace approximation	claim
20	53	Active appearance models for photorealistic visual speech synthesis	claim
21	52	Hierarchical bottle neck features for LVCSR	claim
22	52	A new binary mask based on noise constraints for improved speech intelligibility	claim
23	52	Text normalization based on statistical machine translation and internet user support	claim
24	51	VAD-measure-embedded decoder with online model adaptation	claim
25	51	Binary coding of speech spectrograms using a deep auto-encoder	claim
26	50	Boosted mixture learning of Gaussian mixture HMMs for speech recognition	claim
27	50	Emotion recognition using imperfect speech recognition	claim
28	49	Exploring speaker characteristics for meeting summarization	claim
29	49	A comparative study of constrained and unconstrained approaches for segmentation of speech signal	claim
30	49	Data-dependent evaluator modeling and its application to emotional valence classification from speech	claim
31	49	Learning from human errors: prediction of phoneme confusions based on modified ASR training	claim
32	48	A factorial sparse coder model for single channel source separation	claim
33	48	Prosodic speaker verification using subspace multinomial models with intersession compensation	claim
34	47	Beyond sentence prosody	claim
35	47	Efficient HMM-based estimation of missing features, with applications to packet loss concealment	claim
36	46	Exploring recognition network representations for efficient speech inference on highly parallel platforms	claim
37	46	Online adaptive learning for speech recognition decoding	claim
38	46	Nucleus position within the intonation phrase: a typological study of English, Czech and Hungarian	claim
39	46	Combining many alignments for speech to speech translation	claim
40	45	Phonetic subspace mixture model for speaker diarization	claim
41	45	Invariant integration features combined with speaker-adaptation methods	claim
42	45	Can conversational word usage be used to predict speaker demographics?	claim
43	44	Using a DBN to integrate sparse classification and GMM-based ASR	claim
44	44	Integration of multilayer regression analysis with structure-based pronunciation assessment	claim
45	44	Distribution and trichotomic realization of voiced velars in Japanese - an experimental study	claim
46	43	Combining monaural and binaural evidence for reverberant speech segregation	claim
47	43	The INTERSPEECH 2010 paralinguistic challenge	claim
48	43	A rule-based backchannel prediction model using pitch and pause information	claim
49	43	Brno university of technology system for interspeech 2010 paralinguistic challenge	claim
50	43	The relation between pitch perception preference and emotion identification	claim
51	43	Robust and efficient pitch estimation using an iterative ARMA technique	claim
52	43	Rapid development of speech translation using consecutive interpretation	claim
53	43	Exploiting glottal formant parameters for glottal inverse filtering and parameterization	claim
54	43	Acoustic feature diversity and speaker verification	claim
55	43	Articulatory synthesis and perception of plosive-vowel syllables with virtual consonant targets	claim
56	43	Vocabulary independent spoken query: a case for subword units	claim
57	43	On the interdependencies between voice quality, glottal gaps, and voice-source related acoustic measures	claim
58	43	A procedure for estimating gestural scores from natural speech	claim
59	43	An improved wavelet-based dereverberation for robust automatic speech recognition	claim
60	43	Measuring basic tempo across languages and some implications for speech rhythm	claim
61	42	Towards spoken term discovery at scale with zero resources	claim
62	42	Modeling liaison in French by using decision trees	claim
63	42	Accurate pitch marking for prosodic modification of speech segments	claim
64	42	Semantic facilitation in bilingual everyday speech comprehension	claim
65	42	Multichannel noise reduction using low order RTF estimate	claim
66	42	Hidden Markov models with context-sensitive observations for grapheme-to-phoneme conversion	claim
67	42	A discriminative splitting criterion for phonetic decision trees	claim
68	42	Verifying pronunciation dictionaries using conflict analysis	claim
69	42	The RWTH 2009 quaero ASR evaluation system for English and German	claim
70	42	Landmark-based automated pronunciation error detection	claim
71	42	Phone mismatch penalty matrices for two-stage keyword spotting via multi-pass phone recognizer	claim
72	42	Influence of musical training on perception of L2 speech	claim
73	42	Building transcribed speech corpora quickly and cheaply for many languages	claim
74	41	Canonical state models for automatic speech recognition	claim
75	41	Articulatory-functional modeling of speech prosody: a review	claim
76	41	Can tongue be recovered from face? the answer of data-driven statistical models	claim
77	41	On the relation of Bayes risk, word error, and word posteriors in ASR	claim
78	41	Quality-based playout buffering with FEC for conversational voIP	claim
79	41	Evaluation of speaker mimic technology for personalizing SGD voices	claim
80	41	Voice attributes affecting likability perception	claim
81	41	Direct observation of pruning errors (DOPE): a search analysis tool	claim
82	41	Efficient combined approach for named entity recognition in spoken language	claim
83	40	Robust automatic speech recognition with decoder oriented ideal binary mask estimation	claim
84	40	Combining five acoustic level modeling methods for automatic speaker age and gender recognition	claim
85	40	A comparative large scale study of MLP features for Mandarin ASR	claim
86	40	Laryngealization and features for Chinese tonal recognition	claim
87	40	Modeling pronunciation variation with context-dependent articulatory feature decision trees	claim
88	40	Analyzing user utterances in barge-in-able spoken dialogue system for improving identification accuracy	claim
89	40	Speaker and language adaptive training for HMM-based polyglot speech synthesis	claim
90	40	A spoken term detection framework for recovering out-of-vocabulary words using the web	claim
91	40	Semi-supervised extractive speech summarization via co-training algorithm	claim
92	40	Enhancements of viterbi search for fast unit selection synthesis	claim
93	40	Voice quality evaluation of recent open source codecs	claim
94	40	Learning speaker normalization using semisupervised manifold alignment	claim
95	40	SCARF: a segmental conditional random field toolkit for speech recognition	claim
96	40	Acoustic vector resampling for GMMSVM-based speaker verification	claim
97	40	Improved neural network based language modelling and adaptation	claim
98	40	Expectations for discourse genre identification: a prosodic study	claim
99	40	Decision tree state clustering with word and syllable features	claim
100	39	Dynamic model selection for spectral voice conversion	claim
101	39	Automatic speech recognition for assistive writing in speech supplemented word prediction	claim
102	39	Extending the punctuation module for european portuguese	claim
103	39	Sparse component analysis for speech recognition in multi-speaker environment	claim
104	39	Roles of the average voice in speaker-adaptive HMM-based speech synthesis	claim
105	39	Speech synthesis by modeling harmonics structure with multiple function	claim
106	39	Combination of probabilistic and possibilistic language models	claim
107	39	Lexical entrainment of real users in the let's go spoken dialog system	claim
108	39	Prosody and voice quality of vocal social signals: the case of dominance in scenario meetings	claim
109	39	Combining user intention and error modeling for statistical dialog simulators	claim
110	39	Data pruning for template-based automatic speech recognition	claim
111	38	The influence of actual and perceived sexual orientation on diadochokinetic rate in women and men	claim
112	38	Continuous speech recognition with a TF-IDF acoustic model	claim
113	38	Semi-supervised training of Gaussian mixture models by conditional entropy minimization	claim
114	38	Incremental word learning using large-margin discriminative training and variance floor estimation	claim
115	38	Artificial and online acquired noise dictionaries for noise robust ASR	claim
116	38	Search by voice in Mandarin Chinese	claim
117	38	Automatic selection of thresholds for signal separation algorithms based on interaural delay	claim
118	38	Frequency-domain delexicalization using surrogate vowels	claim
119	38	Voice search for development	claim
120	38	Text-based unstressed syllable prediction in Mandarin	claim
121	38	Manipulating treacheoesophageal speech	claim
122	38	Automatic derivation of phonological rules for mispronunciation detection in a computer-assisted pronunciation training system	claim
123	38	The impact of ASR on abstractive vs. extractive meeting summaries	claim
124	38	Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features	claim
125	38	Wiktionary as a source for automatic pronunciation extraction	claim
126	38	On speaker adaptive training of artificial neural networks	claim
127	38	Convexity and fast speech extraction by split bregman method	claim
128	38	Pitch similarity in the vicinity of backchannels	claim
129	37	Improved real-time MRI of oral-velar coordination using a golden-ratio spiral view order	claim
130	37	Rapid bootstrapping of five eastern european languages using the rapid language adaptation toolkit	claim
131	37	Comparison of HMM and TMDN methods for lip synchronisation	claim
132	37	2010, a speech oddity: phonetic transcription of reversed speech	claim
133	37	Speaking style dependency of formant targets	claim
134	37	HMM-based text-to-articulatory-movement prediction and analysis of critical articulators	claim
135	37	Augmentation of adaptation data	claim
136	37	Performance estimation of noisy speech recognition considering recognition task complexity	claim
137	36	Minimally invasive surgery for spoken dialog systems	claim
138	36	Discriminative adaptation based on fast combination of DMAP and dfMLLR	claim
139	36	AutoBI - a tool for automatic toBI annotation	claim
140	36	Improvements to the equal-parameter BIC for speaker diarization	claim
141	36	Using dependency parsing and machine learning for factoid question answering on spoken documents	claim
142	36	Predicting word accuracy for the automatic speech recognition of non-native speech	claim
143	36	Estimating missing data sequences in x-ray microbeam recordings	claim
144	36	Semi-supervised part-of-speech tagging in speech applications	claim
145	36	On generating combilex pronunciations via morphological analysis	claim
146	36	The relevance of timing, pauses and overlaps in dialogues: detecting topic changes in scenario based meetings	claim
147	36	Study on interaction between entropy pruning and kneser-ney smoothing	claim
148	36	HMM-based automatic visual speech segmentation using facial data	claim
149	35	Paraphrase generation to improve text-to-speech synthesis	claim
150	35	Nonlinear enhancement of onset for robust speech recognition	claim
151	35	Dialect recognition using a phone-GMM-supervector-based SVM kernel	claim
152	35	Language model cross adaptation for LVCSR system combination	claim
153	35	Impact of lack of acoustic feedback in EMG-based silent speech recognition	claim
154	35	Phrase-medial vowel devoicing in spontaneous French	claim
155	35	Mask estimation in non-stationary noise environments for missing feature based robust speech recognition	claim
156	35	Korean lenis, fortis, and aspirated stops: effect of place of articulation on acoustic realization	claim
157	35	Language specific effects of emotion on phoneme duration	claim
158	35	Automatic discriminative measurement of voice onset time	claim
159	35	Multi-pitch estimation by a joint 2-d representation of pitch and pitch dynamics	claim
160	34	Predicting human perception and ASR classification of word-final [t] by its acoustic sub-segmental properties	claim
161	34	The use of subvector quantization and discrete densities for fast GMM computation for speaker verification	claim
162	34	Context adaptive training with factorized decision trees for HMM-based speech synthesis	claim
163	34	On using voice source measures in automatic gender classification of children's speech	claim
164	34	Topic and style-adapted language modeling for Thai broadcast news ASR	claim
165	34	Dialog prediction for a general model of turn-taking	claim
166	34	Prosodic timing analysis for articulatory re-synthesis using a bank of resonators with an adaptive oscillator	claim
167	34	Time conditioned search in automatic speech recognition reconsidered	claim
168	34	Domain adaptation and compensation for emotion detection	claim
169	34	Approaching human listener accuracy with modern speaker verification	claim
170	34	Towards affective state modeling in narrative and conversational settings	claim
171	34	Acoustic feature analysis in speech emotion primitives estimation	claim
172	34	Semi-automated update of automatic transcription system for the Japanese national congress	claim
173	34	Similarity of effects of emotions on the speech organ configuration with and without speaking	claim
174	34	Similarity scoring for recognizing repeated out-of-vocabulary words	claim
175	34	Native and non-native speaker judgements on the quality of synthesized speech	claim
176	34	Feature versus model based noise robustness	claim
177	34	Discriminative adaptation for log-linear acoustic models	claim
178	34	Comparison of approaches for instrumentally predicting the quality of text-to-speech systems	claim
179	33	Morphological and predictability effects on schwa reduction: the case of dutch word-initial syllables	claim
180	33	Rhythm and formant features for automatic alcohol detection	claim
181	33	Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners	claim
182	33	A novel hybrid approach for Mandarin speech synthesis	claim
183	33	Hierarchical multilayer perceptron based language identification	claim
184	33	Relying on critical articulators to estimate vocal tract spectra in an articulatory-acoustic database	claim
185	33	Audio-visual anticipatory coarticulation modeling by human and machine	claim
186	33	Automatic estimation of transcription accuracy and difficulty	claim
187	33	Learning a language model from continuous speech	claim
188	33	Autoregressive clustering for HMM speech synthesis	claim
189	33	FSM-based pronunciation modeling using articulatory phonological code	claim
190	33	Active word learning under uncertain input conditions	claim
191	33	Setup for acoustic-visual speech synthesis by concatenating bimodal units	claim
192	33	HMM-based prosodic structure model using rich linguistic context	claim
193	32	Chirp complex cepstrum-based decomposition for asynchronous glottal analysis	claim
194	32	Unsupervised discovery and training of maximally dissimilar cluster models	claim
195	32	Prominence based scoring of speech segments for automatic speech-to-speech summarization	claim
196	32	Detecting Politeness and efficiency in a cooperative social interaction	claim
197	32	Advanced speech communication system for deaf people	claim
198	32	Automatic speech recognition system channel modeling	claim
199	32	Prominence detection in Swedish using syllable correlates	claim
200	32	Unscented transform with online distortion estimation for HMM adaptation	claim
201	32	Within and across sentence boundary language model	claim
202	32	Investigation of full-sequence training of deep belief networks for speech recognition	claim
203	32	Fully automatic segmentation for prosodic speech corpora	claim
204	32	Competition in the perception of spoken Japanese words	claim
205	32	Investigating articulatory setting - pauses, ready position, and rest - using real-time MRI	claim
206	31	Cross-cultural investigation of prosody in verbal feedback in interactional rapport	claim
207	31	An HMM trajectory tiling (HTT) approach to high quality TTS	claim
208	31	Detecting categorical perception in continuous discrimination data	claim
209	31	Cross-lingual talker discrimination	claim
210	31	Direct construction of compact context-dependency transducers from data	claim
211	31	Improved language recognition using mixture components statistics	claim
212	31	An exploration of voice source correlates of focus	claim
213	31	Exploring web-browser based runtimes engines for creating ubiquitous speech interfaces	claim
214	31	Detection of hot spots in poster conversations based on reactive tokens of audience	claim
215	31	Multimodal speaker diarization using oriented optical flow histograms	claim
216	31	Redescribing intonational categories with functional data analysis	claim
217	31	Strategies for statistical spoken language understanding with small amount of data - an empirical study	claim
218	31	Say what? why users choose to speak their web queries	claim
219	31	Glottal-based analysis of the lombard effect	claim
220	30	Asymptotically exact noise-corrupted speech likelihoods	claim
221	30	What do you mean, you're uncertain?: the interpretation of cue words and rising intonation in dialogue	claim
222	30	On the potential of glottal signatures for speaker recognition	claim
223	30	Influence of lexical tones on intonation in kammu	claim
224	30	Reduction of broadband noise in speech signals by multilinear subspace analysis	claim
225	30	Validation of a training method for L2 continuous-speech segmentation	claim
226	30	Frequency of occurrence effects on pitch accent realisation	claim
227	30	Regularized-MLLR speaker adaptation for computer-assisted language learning system	claim
228	30	Constructing Japanese test collections for spoken term detection	claim
229	30	An intonation model for TTS in sepedi	claim
230	30	Augmented set of features for confidence estimation in spoken term detection	claim
231	29	A spectral LF model based approach to voice source parameterisation	claim
232	29	Shape-invariant speech transformation with the phase vocoder	claim
233	29	Improving monaural speaker identification by double-talk detection	claim
234	29	HMM adaptation using linear spline interpolation with integrated spline parameter training for robust speech recognition	claim
235	29	Exploring the mechanism of tonal contraction in taiwan Mandarin	claim
236	29	Full body aero-tactile integration in speech perception	claim
237	28	Towards mixed language speech recognition systems	claim
238	28	Non-negative matrix factorization based compensation of music for automatic speech recognition	claim
239	27	The prosody of Swedish conversational grunts	claim
240	27	Disambiguating the functions of conversational sounds with prosody: the case of yeah	claim
241	27	Phonetic realization of second occurrence focus in Japanese	claim
242	26	A classifier-based target cost for unit selection speech synthesis trained on perceptual data	claim
243	26	Improvements of search error risk minimization in viterbi beam search for speech recognition	claim
244	23	Reducing musical noise in blind source separation by time-domain sparse filters and split bregman method	claim
245	23	The role of higher-level linguistic features in HMM-based speech synthesis	claim
246	22	Specification in context - devoicing processes in Polish, French, american English and German sonorants	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers