2000 IEEE international conference on acoustics, speech, and signal processing

PDF

Author Index (Abstract)

pp. A1-A11

PDF

Tied posteriors: an approach for effective introduction of context dependency in hybrid NN/HMM LVCSR (Abstract)

J. Rottland, Dept. of Comput. Sci., Gerhard-Mercator-Univ. Duisburg, Germany

G. Rigoll

pp. 1241-1244

PDF

Discriminative resolution enhancement in acoustic modelling (Abstract)

J. Duchateau, ESAT, Katholieke Univ., Leuven, Heverlee, Belgium

K. Demuynck

P. Wambacq

pp. 1245-1248

PDF

A segmental-feature HMM using parametric trajectory model (Abstract)

Young-Sun Yun, Dept. of Comput. Sci., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea

Yung-Hwan Oh

pp. 1249-1252

PDF

Soft GPD for minimum classification error rate training (Abstract)

B.E. Shi, Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Kowloon, China

Kaisheng Yao

Zhigang Cao

pp. 1253-1256

PDF

Heterogeneous lexical units for automatic speech recognition: preliminary investigations (Abstract)

I. Bazzi, Lab. for Comput. Sci., MIT, Cambridge, MA, USA

J. Glass

pp. 1257-1260

PDF

Acoustic modeling for Chinese speech recognition: a comparative study of Mandarin and Cantonese (Abstract)

Sheng Gao, Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China

Tan Lee

Bo Xu

pp. 1261-1264

PDF

An effective acoustic modeling of names based on model induction (Abstract)

Taeyoon Kim, Dept. of Electron. Eng., Korea Univ., Seoul, South Korea

Sunmee Kang

Hanseok Ko

pp. 1265-1268

PDF

A new phonetic tied-mixture model for efficient decoding (Abstract)

A. Lee, Kyoto Univ., Japan

pp. 1269-1272

PDF

Agglomerative vs. tree-based clustering for the definition of multilingual set of triphones (Abstract)

B. Imperl, Fac. of Electr. Eng. & Comput. Sci., Maribor Univ., Slovenia

pp. 1273-1276

PDF

Integrating dynamic speech modalities into context decision trees (Abstract)

C. Fugen, Interactive Syst. Lab., Karlsruhe Univ., Germany

I. Rogina

pp. 1277-1280

PDF

A novel approach to the fully automatic extraction of Fujisaki model parameters (Abstract)

H. Mixdorff, Tech. Univ. Dresden, Germany

pp. 1281-1284

PDF

Robust generation of symbolic prosody by a neural classifier based on autoassociators (Abstract)

A.F. Muller, Siemens Corp., Munich, Germany

H.G. Zimmermann

R. Neuneier

pp. 1285-1288

PDF

Improving intonational phrasing with syntactic information (Abstract)

P. Koehn, AT&T Res., Florham Park, NJ, USA

pp. 1289-1290

PDF

Automatic learning of numeral grammars for multi-lingual speech synthesizers (Abstract)

G. Flach, Lab. of Acoust. & Speech Commun., Tech. Univ. Dresden, Germany

C. Just

pp. 1291-1294

PDF

Time and frequency scale modification of speech signals (Abstract)

B. Ninness, Dept. of Electr. & Comput. Eng., Newcastle Univ., Callaghan, NSW, Australia

S. Henriksen

pp. 1295-1298

PDF

Speech reconstruction from mel frequency cepstral coefficients and pitch frequency (Abstract)

D. Chazan, IBM Res. Lab., Haifa, Israel

pp. 1299-1302

PDF

Improving the robustness of wavelet transform for epoch detection (Abstract)

Y.Y. Lam, Dept. of Comput., Hong Kong Polytech. Univ., China

R.W.P. Luk

F.L. Chung

pp. 1303-1306

PDF

A weighted autocorrelation method for pitch extraction of noisy speech (Abstract)

H. Kobayashi, Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan

T. Shimamura

pp. 1307-1310

PDF

Performance of the pitch-scaled harmonic filter and applications in speech analysis (Abstract)

P.J.B. Jackson, Dept. of Electron. & Comput. Sci., Southampton Univ., UK

C.H. Shadle

pp. 1311-1314

PDF

Speech parameter generation algorithms for HMM-based speech synthesis (Abstract)

K. Tokuda, Dept. of Comput. Sci., Nagoya Inst. of Technol., Japan

pp. 1315-1318

PDF

Unsupervised estimation of the human vocal tract length over sentence level utterances (Abstract)

B.F. Necioglu, Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

M.A. Clements

pp. 1319-1322

PDF

Multivariate-state hidden Markov models for simultaneous transcription of phones and formants (Abstract)

M. Hasegawa-Johnson, Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA

pp. 1323-1326

PDF

On the mutual information between frequency bands in speech (Abstract)

M. Nilsson, Dept. of Speech Music & Hearing, R. Inst. of Technol., Stockholm, Sweden

S.V. Andersen

W.B. Kleijn

pp. 1327-1330

PDF

Study of talker individuality by using ARX speech analysis-synthesis-editing system (Abstract)

Weizhong Zhu, Adv. Technol. Res. Lab., Matsushita Electr. Ind. Co. Ltd., Kyoto, Japan

K. Matsui

H. Kasuya

pp. 1331-1334

PDF

Linguistic properties of non-native speech (Abstract)

L.M. Tomokiyo, Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA

pp. 1335-1338

PDF

Visual approach for automatic pitch period estimation (Abstract)

Zhang Sen, Dept. of Inf. & Comput. Sci., Waseda Univ., Tokyo, Japan

K. Shirai

pp. 1339-1342

PDF

Robust pitch tracking for prosodic modeling in telephone speech (Abstract)

Chao Wang, Lab. for Comput. Sci., MIT, Cambridge, MA, USA

S. Seneff

pp. 1343-1346

PDF

Perceptual effects of coarticulation in fricatives (Abstract)

S. Fernandez, Dept. of Appl. Phys., Santiago de Compostela Univ., Spain

pp. 1347-1350

PDF

Mel-scaled discrete wavelet coefficients for speech recognition (Abstract)

J.N. Gowdy, Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA

Z. Tufekci

pp. 1351-1354

PDF

On-line speaking rate estimation using Gaussian mixture models (Abstract)

R. Faltlhauser, Inst. for Human-Machine-Commun., Tech. Univ. of Munich, Germany

T. Pfau

G. Ruske

pp. 1355-1358

PDF

Waveform extraction for perfect reconstruction in WI coding (Abstract)

V.T. Ruoppila, Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada

M. Tammi

J. Saarinen

pp. 1359-1362

PDF

High quality enhanced waveform interpolative coding at 2.8 kbps (Abstract)

O. Gottesman, Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA

A. Gersho

pp. 1363-1366

PDF

Analysis-by-synthesis multimode harmonic speech coding at 4 kb/s (Abstract)

Chunyan Li, Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA

V. Cuperman

pp. 1367-1370

PDF

Speech coding with an analysis-by-synthesis sinusoidal model (Abstract)

C.O. Etemoglu, Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA

V. Cuperman

A. Gersho

pp. 1371-1374

PDF

A 1200 bps speech coder based on MELP (Abstract)

Tian Wang, SignalCom Inc., Goleta, CA, USA

pp. 1375-1378

PDF

A 4 kb/s hybrid MELP/CELP coder with alignment phase encoding and zero-phase equalization (Abstract)

J. Stachurski, DSP Solutions R&D Center, Texas Instrum., Dallas, TX, USA

A. McCree

pp. 1379-1382

PDF

Perceptual phase redundancy in speech (Abstract)

Doh-Suk Kim, Human & Comput. Interaction Lab., Samsung Adv. Inst. of Technol., Kyonggi, South Korea

pp. 1383-1386

PDF

A combined WI and MELP coder at 5.2 kbps (Abstract)

J. Skoglund, AT&T Labs.-Res., Florham Park, NJ, USA

R.V. Cox

J.S. Collura

pp. 1387-1390

PDF

A background noise reduction technique based on sinusoidal speech coding systems (Abstract)

S. Yeldener, COMSAT Lab., Clarksburg, MD, USA

J.H. Rieser

pp. 1391-1394

PDF

Variable rate multi-mode excitation coding of speech at 2.4 kbps (Abstract)

Shihua Wang, Atmel Corp., Berkeley, CA, USA

pp. 1395-1398

PDF

Speech/non-speech classification using multiple features for robust endpoint detection (Abstract)

Won-Ho Shin, Inf. Technol. Lab., LG Corp. Inst. of Technol., South Korea

pp. 1399-1402

PDF

Speech recognition for a distant moving speaker based on HMM composition and separation (Abstract)

T. Takiguchi, IBM Tokyo Res. Lab., Kanagawa, Japan

S. Nakamura

K. Shikano

pp. 1403-1406

PDF

Hands-free speech recognition using a filtered clean corpus and incremental HMM adaptation (Abstract)

M. Matassoni, Centro per la Ricerca Sci. e Technol., Povo di Trento, Italy

M. Omologo

D. Giulini

pp. 1407-1410

PDF

HMM adaptation and microphone array processing for distant speech recognition (Abstract)

J. Kleban, CAIP Center, Rutgers Univ., Piscataway, NJ, USA

Y. Gong

pp. 1411-1414

PDF

Comparing acoustic features for robust ASR in fixed and cellular network applications (Abstract)

F. de Wet, Dept. of Language & Speech, Nijmegen Univ., Netherlands

pp. 1415-1418

PDF

Anchoring hypothesis and its application to tone recognition of Chinese continuous speech (Abstract)

J.-S. Zhang, Dept. of Inf. & Commun. Eng., Tokyo Univ., Japan

K. Hirose

pp. 1419-1422

PDF

Strategies for automatic segmentation of audio data (Abstract)

T. Kemp, Interactive Syst. Labs., Karlsruhe Univ., Germany

pp. 1423-1426

PDF

A method for direct audio search with applications to indexing and retrieval (Abstract)

S.E. Johnson, Dept. of Eng., Cambridge Univ., UK

P.C. Woodland

pp. 1427-1430

PDF

The study on distributed speech recognition system (Abstract)

WeiQi Zhang, Archit. Dev. Lab., Intel Corp., China

pp. 1431-1434

PDF

Conversational speech recognition using acoustic and articulatory input (Abstract)

K. Kirchhoff, Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

G.A. Fink

G. Sagerer

pp. 1435-1438

PDF

Harmonic exponential modeling of transitional speech segments (Abstract)

J. Jensen, Center for PersonKommunikation, Aalborg Univ., Denmark

S.H. Jensen

E. Hansen

pp. 1439-1442

PDF

Variable dimensional algebraic CELP coding of prototype waveforms (Abstract)

Jongseo Sohn, Sch. of Electr. Eng., Seoul Nat. Univ., South Korea

Wonyong Sung

pp. 1443-1446

PDF

Low-rate quantization of spectrum parameters (Abstract)

T. Eriksson, Dept. of Signals & Syst., Chalmers Univ. of Technol., Goteborg, Sweden

H.-G. Kang

P. Hedelin

pp. 1447-1450

PDF

Recursive LPC spectrum coding-a classified VQ approach (Abstract)

F. Norden, Inf. Theory Lab., Chalmers Univ. of Technol., Goteborg, Sweden

J. Samuelsson

P. Hedelin

pp. 1451-1454

PDF

Robust application of discrete all-pole modeling to sinusoidal transform coding (Abstract)

D.J. Molyneux, Dept. of Comput. Sci., Manchester Univ., UK

M.S. Ho

B.M.G. Cheetham

pp. 1455-1458

PDF

Predictive and mel-scale binary vector quantization of variable dimension spectral magnitude (Abstract)

B.M.G. Cheetham, CCSR, Surrey Univ., Guildford, UK

B.M.G. Cheetham

A. Kondoz

pp. 1459-1462

PDF

Encoding sinusoidal amplitudes with a minimum phase rational model (Abstract)

N. Malik, Sch. of Electr. Eng. & Telecommun., New South Wales Univ., Sydney, NSW, Australia

W.H. Holmes

pp. 1463-1466

PDF

Phase and transient modeling for harmonic+noise speech coding (Abstract)

E.W.M. Yu, Dept. of Electr. Eng., City Univ. of Hong Kong, Kowloon, China

Cheung-Fat Chan

pp. 1467-1470

PDF

Linear prediction incorporating simultaneous masking (Abstract)

J. Lukasiak, Whisper Labs., Wollongong Univ., NSW, Australia

pp. 1471-1474

PDF

A frame interpretation of sinusoidal coding and waveform interpolation (Abstract)

W. Bastiaan Kleijn, Dept. of Speech, Music & Hearing, R. Inst. of Technol., Stockholm, Sweden

pp. 1475-1478

PDF

Optimized estimation of spectral parameters for the coding of noisy speech (Abstract)

R. Martin, Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany

I. Wittke

P. Jax

pp. 1479-1482

PDF

Improved frame erasure concealment for CELP-based coders (Abstract)

J.C. de Martin, DSPS R&D, Texas Instrum. Inc., Dallas, TX, USA

T. Unno

V. Viswanathan

pp. 1483-1486

PDF

A CELP-based hybrid digital-analog (HDA) joint source-channel speech coder (Abstract)

N. Phamdo, Dept. of Electr. & Comput. Eng., State Univ. of New York, Stony Brook, NY, USA

U. Mittal

pp. 1487-1490

PDF

Pitch-synchronous linear-prediction analysis by synthesis with reduced pulse densities (Abstract)

D. Guerchi, INTS-Telecommun., Univ. du Quebec, Verdun, Que., Canada

Y. Qian

P. Mermelstein

pp. 1491-1494

PDF

Shaped fixed codebook search for CELP coding at low bit rates (Abstract)

E. Erzin, Lucent Technol. Bell. Labs., Whippany, NJ, USA

pp. 1495-1498

PDF

Digital watermarking of speech signals for the National Gallery of the Spoken Word (Abstract)

F.J. Ruiz, Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA

F.J. Ruiz

pp. 1499-1502

PDF

Dispersed-pulse codebook and its application to a 4 kb/s speech coder (Abstract)

K. Yasunaga, Mobile Commun. Res. Lab., Matsushita Res. Inst. Tokyo Inc., Kawasaki, Japan

pp. 1503-1506

PDF

Joint source-channel MMSE-decoding of speech parameters (Abstract)

S. Heinen, Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany

P. Vary

pp. 1507-1510

PDF

Speech quality objective assessment using neural network (Abstract)

Qiang Fu, Nat. Key Lab. of ISN, Xidian Univ., Xi'an, China

Kechu Yi

Mingui Sun

pp. 1511-1514

PDF

The perceptual analysis measurement system for robust end-to-end speech quality assessment (Abstract)

A.W. Rix, BT Adv. Commun. Res., Ipswich, UK

M.P. Hollier

pp. 1515-1518

PDF

Rapid likelihood calculation of subspace clustered Gaussian components (Abstract)

A. Aiyer, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

M.J.F. Gales

M.A. Picheny

pp. 1519-1522

PDF

Pitch tracking and tone features for Mandarin speech recognition (Abstract)

M.A. Picheny, Philips Innovation Center, Taipei, Taiwan

F. Seide

pp. 1523-1526

PDF

Boosting Gaussian mixtures in an LVCSR system (Abstract)

G. Zweig, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

M. Padmanabhan

pp. 1527-1530

PDF

Using SIMD instructions for fast likelihood calculation in LVCSR (Abstract)

S. Kanthak, Lehrstuhl fur Inf. VI, Tech. Hochschule Aachen, Germany

K. Schutz

H. Ney

pp. 1531-1534

PDF

Fast decoding in large vocabulary name dialing (Abstract)

J. Suontausta, Speech & Audio Syst. Lab., Nokia Res. Center, Tampere, Finland

J. Hakkinen

O. Viikki

pp. 1535-1538

PDF

On the incremental addition of regression classes for speaker adaptation (Abstract)

J. McDonough, Center for Language & Speech Processing, Johns Hopkins Univ., Baltimore, MD, USA

V. Venkatoramani

W. Byrne

pp. 1539-1542

PDF

Inter-class MLLR for speaker adaptation (Abstract)

S.-J. Doh, Carnegie Mellon Univ., Pittsburgh, PA, USA

R. Stern

pp. 1543-1546

PDF

Model adaptation in line spectrum domain (Abstract)

An-Tze Yu, Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan

Hsiao-Chuan Wang

pp. 1547-1550

PDF

MAP adaptation with subspace regression classes and tying (Abstract)

Kwok-Man Wong, Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., Clear Water Bay, China

B. Mak

pp. 1551-1554

PDF

DUcoder-the Duisburg University LVCSR stackdecoder (Abstract)

D. Willett, Dept. of Comput. Sci., Gerhard-Mercator-Univ., Duisburg, Germany

C. Neukirchen

G. Rigoll

pp. 1555-1558

PDF

Progressive 2-pass decoder for real-time broadcast news captioning (Abstract)

T. Imai, NHK Sci. & Tech. Res. Labs., Tokyo, Japan

A. Kobayashi

S. Sato

H. Tanaka

A. Ando

pp. 1559-1562

PDF

Turkish LVCSR: towards better speech recognition for agglutinative languages (Abstract)

K. Carki, Interactive Syst. Labs., Karlsruhe Univ., Germany

P. Geutner

T. Schultz

pp. 1563-1566

PDF

Performance of LVCSR with morpheme-based and syllable-based recognition units (Abstract)

Oh-Wook Kwon, ETRI, Taejon, South Korea

pp. 1567-1570

PDF

Employing heterogeneous information in a multi-stream framework (Abstract)

H. Christensen, Center for PersonKommunikation, Aalborg Univ., Denmark

B. Lindberg

O. Andersen

pp. 1571-1574

PDF

Dictation of multiparty conversation using statistical turn taking model and speaker model (Abstract)

N. Murai, Dept. of Electr., Electron., & Comput. Eng., Waseda Univ., Tokyo, Japan

T. Kobayashi

pp. 1575-1578

PDF

Automatic speech summarization based on word significance and linguistic likelihood (Abstract)

C. Hori, Dept. of Comput. Sci., Tokyo Inst. of Technol., Japan

S. Furui

pp. 1579-1582

PDF

Statistical knowledge based frame synchronous search strategies in continuous speech recognition (Abstract)

Zhanjiang Song, Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China

Fang Zheng

Wenhu Wu

pp. 1583-1586

PDF

Using posterior word probabilities for improved speech recognition (Abstract)

F. Wessel, Lehrstuhl fur Inf., Tech. Hochschule Aachen, Germany

R. Schluter

H. Ney

pp. 1587-1590

PDF

Variable word rate N-grams (Abstract)

Y. Gotoh, Dept. of Comput. Sci., Sheffield Univ., UK

S. Renals

pp. 1591-1594

PDF

Integrating detailed information into a language model (Abstract)

Ruiqiang Zhang, ATR Interpreting Telephony Res. Labs., Kyoto, Japan

pp. 1595-1598

PDF

An optimal Bhattacharyya centroid algorithm for Gaussian clustering with applications in automatic speech recognition (Abstract)

L. Rigazio, Speech Technol. Lab., Panasonic Technols Inc., Santa Barbara, CA, USA

B. Tsakam

J.-C. Junqua

pp. 1599-1602

PDF

Ear-model derived features for automatic speech recognition (Abstract)

R. De Mori, LIA CERI-IUP, Univ. of Avignon, France

D. Albesano

R. Gemello

F. Mana

pp. 1603-1606

PDF

Bitstream-based feature extraction for wireless speech recognition (Abstract)

F. Mana, AT&T Labs.-Res., Florham Park, NJ, USA

R. Cox

pp. 1607-1610

PDF

A fuzzy approach for the equalization of cepstral variances (Abstract)

Wei-Wen Hung, Dept. of Electr. Eng., Ming-Chi Inst. of Technol., Taishan, Taiwan

Hsiao-Chuan Wang

pp. 1611-1614

PDF

A new approach to discriminative feature extraction using model transformation (Abstract)

M. Thomae, Res. & Technol., DaimlerChrysler AG, Ulm, Germany

G. Ruske

T. Pfau

pp. 1615-1618

PDF

A Markov random field based multi-band model (Abstract)

G. Gravier, ENST/TSI, CNRS, Paris, France

M. Sigelle

G. Chollet

pp. 1619-1622

PDF

Auditory-based speech processing based on the average localized synchrony detection (Abstract)

A.M. Abdelatty Ali, Dept. of Electr. Eng., Pennsylvania Univ., Philadelphia, PA, USA

J. Van Der Speigel

P. Mueller

pp. 1623-1626

PDF

Data-driven RASTA filters in reverberation (Abstract)

M.L. Shire, Int. Comput. Sci. Inst., California Univ., Berkeley, CA, USA

B.Y. Chen

pp. 1627-1630

PDF

Speech feature extraction using independent component analysis (Abstract)

Jong-Hwan Lee, Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea

pp. 1631-1634

PDF

Tandem connectionist feature extraction for conventional HMM systems (Abstract)

H. Hermansky, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA

D.P.W. Ellis

S. Sharma

pp. 1635-1638

PDF

A unified context-free grammar and n-gram model for spoken language processing (Abstract)

Ye-Yi Wang, Speech Technol. Group, Microsoft Corp., Redmond, WA, USA

M. Mahajan

Xuedong Huang

pp. 1639-1642

PDF

Integrating a context-dependent phrase grammar in the variable n-gram framework (Abstract)

Manhung Siu, Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Clearwater Bay, China

M. Ostendorf

pp. 1643-1646

PDF

Putting it all together: language model combination (Abstract)

J.T. Goodman, Speech Technol. Group, Microsoft Corp., Redmond, WA, USA

pp. 1647-1650

PDF

Towards a large-vocabulary French vocal dictation based on a size-independent language-model search using the INRS recognizer (Abstract)

H. Tolba, INRS-Telecommun., Verdun, Que., Canada

D. O'Shaughnessy

pp. 1651-1654

PDF

Large vocabulary decoding and confidence estimation using word posterior probabilities (Abstract)

G. Evermann, Dept. of Eng., Cambridge Univ., UK

P.C. Woodland

pp. 1655-1658

PDF

Efficient integration of multiple pronunciations in a large vocabulary decoder (Abstract)

H. Schramm, Philips Res. Lab., Aachen, Germany

X.L. Aubert

pp. 1659-1662

PDF

Transcription and indexation of broadcast data (Abstract)

J.-L. Gauvnin, Spoken Language Process. Group, LIMSI-CNRS, Orsay, France

L. Lamel

Y. De Kercadio

G. Adda

pp. 1663-1666

PDF

A baseline for the transcription of Italian broadcast news (Abstract)

F. Brugnara, Centro per la Ricerca Sci. e Tecnol., ITC-irst, Trento, Italy

pp. 1667-1670

PDF

Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech (Abstract)

A. Sixtus, Luhrstuhl fur Inf., Tech. Hochschule Aachen, Germany

S. Molau

S. Kanthak

R. Schluter

H. Ney

pp. 1671-1674

PDF

French large vocabulary recognition with cross-word phonology transducers (Abstract)

G. Boulianne, Centre de Recherche Inf. de Montreal, Que., Canada

pp. 1675-1678

PDF

Pronunciation ambiguity vs. pronunciation variability in speech recognition (Abstract)

M. Saraclar, Centre for Language & Speech Processing, Johns Hopkins Univ., Baltimore, MD, USA

S. Khudanpur

pp. 1679-1682

PDF

Lexical modeling of non-native speech for automatic speech recognition (Abstract)

K. Livescu, Spoken Language Res. Group, MIT, Cambridge, MA, USA

J. Glass

pp. 1683-1686

PDF

Data-driven generation of pronunciation dictionaries in the German Verbmobil project: discussion of experimental results (Abstract)

M. Eichner, Lab. of Acoustics & Speech Commun., Tech. Univ. Dresden, Germany

M. Wolff

pp. 1687-1690

PDF

Automatic generation of phone sets and lexical transcriptions (Abstract)

R. Singh, Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA

B. Raj

R.M. Stern

pp. 1691-1694

PDF

Selecting articles from the language model training corpus (Abstract)

D. Klakow, Philips GmbH Forschungslab., Aachen, Germany

pp. 1695-1698

PDF

Syntactic heads in statistical language modeling (Abstract)

Jun Wu, Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA

S. Khudanpur

pp. 1699-1702

PDF

A unified approach to statistical language modeling for Chinese (Abstract)

Jianfeng Gao, Microsoft Res., Beijing, China

pp. 1703-1706

PDF

Polyphone decision tree specialization for language adaptation (Abstract)

T. Schultz, Interactive Syst. Labs., Karlsruhe Univ., Germany

A. Waibel

pp. 1707-1710

PDF

Enhanced language modelling with phonologically constrained morphological analysis (Abstract)

A.C. Fang, Dept. of Phonetics & Linguistics, Univ. Coll. London, UK

M. Huckvale

pp. 1711-1714

PDF

Long range language models for free spelling recognition (Abstract)

F. Thiele, Philips Res. Lab., Aachen, Germany

B. Rueber

D. Klakow

pp. 1715-1718

PDF

Model-based feature enhancement for noisy speech recognition (Abstract)

C. Couvreur, Lernout & Hauspie Speech Products, Wemmel, Belgium

H. Van Hamme

pp. 1719-1722

PDF

Robust speech recognition using near-field superdirective beamforming with post-filtering (Abstract)

I.A. McCowan, Speech Res. Lab., Queensland Univ. of Technol., Brisbane, Qld., Australia

C. Marro

L. Mauuary

pp. 1723-1726

PDF

Noisy speech recognition using noise reduction method based on Kalman filter (Abstract)

M. Fujimoto, Dept. of Electron. & Inf., Ryukoku Univ., Ohtsu, Japan

Y. Ariki

pp. 1727-1730

PDF

Statistical estimation of unreliable features for robust speech recognition (Abstract)

P. Renevey, Signal Process. Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland

A. Drygajlo

pp. 1731-1734

PDF

Hands-free voice activation of personal communication devices (Abstract)

S.E. Bou-Ghazale, Media Access Speech Technol. Dev., Conexant Syst. Inc., Newport Beach, CA, USA

A.O. Asadi

pp. 1735-1738

PDF

An acoustic measure for predicting recognition performance degradation (Abstract)

K. Takeda, Grad. Sch. of Eng., Nagoya Univ., Japan

M. Kondo

F. Itakura

pp. 1739-1742

PDF

Low complexity speaker independent command word recognition in car environments (Abstract)

S.K. Riis, Digital Signal Processing Group, Nokia Mobile Phones, Copenhagen, Denmark

O. Viikki

pp. 1743-1746

PDF

Speech recognition based on space diversity using distributed multi-microphone (Abstract)

Y. Shimizu, Grad. Sch. of Eng., Nagoya Univ., Japan

pp. 1747-1750

PDF

A novel approach to robust speech endpoint detection in car environments (Abstract)

Liang-Sheng Huang, Panasonic Taiwan Labs. Co., Taipei, Taiwan

Chung-Ho Yang

pp. 1751-1754

PDF

Detecting the end of spellings using statistics on recognized letter sequences for spelled names recognition (Abstract)

S. Hanel, CNET/DIH/DIP, France Telecom, Lannion, France

D. Jouvet

pp. 1755-1758

PDF

Decision tree based Mandarin tone model and its application to speech recognition (Abstract)

Yang Cao, Nat. Lab. of Pattern Recog., Acad. Sinica, Beijing, China

Yonggang Deng

Hong Zhang

Taiyi Huang

Bo Xu

pp. 1759-1762

PDF

Detection of prosodic word boundaries by statistical modeling of mora transitions of fundamental frequency contours and its use for continuous speech recognition (Abstract)

K. Hirose, Sch. of Frontier Sci., Tokyo Univ., Japan

K. Iwano

pp. 1763-1766

PDF

Parameter optimization for vocal tract length normalization (Abstract)

P. Dognin, Dept. of Electr. Eng., Pittsburgh Univ., PA, USA

A. El-Jaroudi

J. Billa

pp. 1767-1770

PDF

Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics (Abstract)

Berlin Chen, Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan

Hsin-Min Wang

Lin-Shan Lee

pp. 1771-1774

PDF

Word-level rate of speech modeling using rate-specific phones and pronunciations (Abstract)

Jing Zheng, Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA

pp. 1775-1778

PDF

Specialized acoustic models for hyperarticulated speech (Abstract)

H. Soltau, Karlsruhe Univ., Germany

A. Waibel

pp. 1779-1782

PDF

On the use of variable frame rate analysis in speech recognition (Abstract)

Qifeng Zhu, Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA

A. Alwan

pp. 1783-1786

PDF

A probabilistic union model for sub-band based robust speech recognition (Abstract)

Ji Ming, Sch. of Comput. Sci., Queen's Univ., Belfast, UK

F.J. Smith

pp. 1787-1790

PDF

Robust speech recognition over IP networks (Abstract)

B. Milner, BT Adastral Park, Adv. Communs. Eng., Martlesham Heath, UK

S. Semnani

pp. 1791-1794

PDF

Fast speaker adaptation of artificial neural networks for automatic speech recognition (Abstract)

S. Dupont, TCTS-MULTITEL, Faculte Polytech. de Mons, Belgium

L. Cheboub

pp. 1795-1798

PDF

Word and phone level acoustic confidence scoring (Abstract)

S.O. Kamppari, Spoken Language Syst. Group, MIT, Cambridge, MA, USA

T.J. Hazen

pp. 1799-1802

PDF

Contextual confidence measures for continuous speech recognition (Abstract)

G. Hernandez-Abrego, Dept. de Teoria del Senyal i Comunicacions, Univ. Politecnica de Catalunya, Barcelona, Spain

J.B. Marino

pp. 1803-1806

PDF

Confidence measure and incremental adaptation for the rejection of incorrect data (Abstract)

N. Moreau, CNET/DIH/DIPS, France Telecom, Lannion, France

D. Charlet

D. Jouvet

pp. 1807-1810

PDF

Robust out-of-vocabulary rejection for low-complexity speaker independent speech recognition (Abstract)

C.C. Broun, Human Interface Lab., Motorola Inc., Tempe, AZ, USA

W.M. Campbell

pp. 1811-1814

PDF

Meta-models for confidence estimation in speech recognition (Abstract)

S. Dasmahapatra, Sch. of Inf. Syst., Univ. of East Anglia, Norwich, UK

S. Cox

pp. 1815-1818

PDF

Evaluation of various confidence-based strategies for isolated word rejection (Abstract)

E. Tsiporkova, Speech Recognition Res., Lernout & Hauspie, Wemmel, Belgium

F. Vanpoucke

H. Van Hamme

pp. 1819-1822

PDF

Use of word level side information to improve speech recognition (Abstract)

D. Vergyri, Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA

pp. 1823-1826

PDF

Confidence measure based language identification (Abstract)

F. Metze, Interactive Syst. Lab., Karlsruhe Univ., Germany

T. Kemp

pp. 1827-1830

PDF

A new keyword spotting approach based on iterative dynamic programming (Abstract)

M. Silaghi, Artificial Intelligence Lab., Swiss Fed. Inst. of Technol., Lausanne, Switzerland

H. Bourlard

pp. 1831-1834

PDF

Frame-discriminative and confidence-driven adaptation for LVCSR (Abstract)

F. Wallhoff, Dept. of Comput. Sci., Gerhard-Mercator Univ. Duisberg, Germany

D. Willett

G. Rigoll

pp. 1835-1838

PDF

An adaptive subspace approach for speech enhancement (Abstract)

S. Gazor, Dept. of Electr. & Comput. Eng., Queen's Univ., Kingston, Ont., Canada

A. Rezayee

pp. 1839-1842

PDF

Narrowband to wideband conversion of speech using GMM based transformation (Abstract)

Kun-Youl Park, Dept. of Electron. Eng., Pusan Nat. Univ., South Korea

Kun-Youl Park

pp. 1843-1846

PDF

Signal/noise KLT based approach for enhancing speech degraded by colored noise (Abstract)

U. Mittal, Dept. of Electr. & Comput. Eng., State Univ. of New York, Stony Brook, NY, USA

N. Phamdo

pp. 1847-1850

PDF

Low-band extension of telephone-band speech (Abstract)

G. Miet, Philips Consumer Commun., Le Mans, France

A. Gerrits

J.C. Valiere

pp. 1851-1854

PDF

A hybrid speech enhancement system based on HMM and spectral subtraction (Abstract)

M.H. Ghoreishi, Dept. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran

H. Sheikhzadeh

pp. 1855-1858

PDF

Enhancement of speech based on non-parametric estimation of a time varying harmonic representation (Abstract)

S. Dubost, Dept. TSI/LTCI, Ecole Nat. Superieure des Telecommun., Paris, France

O. Cappe

pp. 1859-1862

PDF

Integrated noise reduction and echo cancellation for IS-136 systems (Abstract)

F. Basbug, Hughes Network Syst. Inc., Germantown, MD, USA

K. Swaminathan

S. Nandkumar

pp. 1863-1866

PDF

An improved cumulant-based blind speech separation method (Abstract)

Yeping Su, Hughes Network Syst. Inc., Germantown, MD, USA

Liang He

RongZhen Yang

pp. 1867-1870

PDF

Impulsive noise suppression using neural networks (Abstract)

I. Potamitis, Dept. of Electr. & Comput. Eng., Patras Univ., Greece

N.D. Fakotakis

G. Kokkinakis

pp. 1871-1874

PDF

Quantile based noise estimation for spectral subtraction and Wiener filtering (Abstract)

V. Stahl, Philips Res. Lab., Aachen, Germany

A. Fischer

R. Bippus

pp. 1875-1878

PDF