SP Subject Index 1995

{SP95-1} M. Hashimoto and N. Higuchi, 
``Spectral mapping for voice conversion using speaker selection and vector field smoothing,''
IEICE Technical Report, SP95-1, pp.1--8, May 1995.
{ speech synthesis, voice conversion, spectral mapping, speaker selection, vector field smoothing }

{SP95-2} Y. Endo and H. Kasuya, 
``An analysis-conversion-synthesis system for pathological voice and its application,''
IEICE Technical Report, SP95-2, pp.9--14, May 1995.
{ pathological voice, perturbation, ARMA model, perceptual impression }

{SP95-3} W. Ding and H. Kasuya, 
``ARX model of speech production and estimation of vocal tract and voice source parameters,''
IEICE Technical Report, SP95-3, pp.15--22, May 1995.
{ ARX model, voice source model, harmonic characteristics, pitch extraction }

{SP95-4} T. Matsushita, W. Ding, M. Matsuda, S. Hayakawa, C. S. Yang and H. Kasuya, 
``Speech synthesis based on formant parameter templates,''
IEICE Technical Report, SP95-4, pp.23--30, May 1995.
{ speech synthesis, formant, templates concatenative method }

{SP95-5} Y. Ishikawa and K. Nakajima, 
``Speech synthesis by rule based on synthesis unit considering prosodic features,''
IEICE Technical Report, SP95-5, pp.31--38, May 1995.
{ speech synthesis, synthesis by rule, spectral control, prosody, synthesis unit, clustering }

{SP95-6} M. Sakamoto, T. Saito, K. Suzuki, Y. Hashimoto and M. Kobayashi, 
``A new waveform overlap-add technique for text-to-speech synthesis,''
IEICE Technical Report, SP95-6, pp.39--45, May 1995.
{ text-to-speech, waveform overlap-add, glottal closure instants, wavelet transform }

{SP95-7} H. Kawai and S. Yamamoto, 
``Constructing a waveform inventory for text-to-speech synthesis
taking account of fundamental frequency and phoneme duration,''
IEICE Technical Report, SP95-7, pp.47--52, May 1995.
{ speech synthesis, waveform splicing, PSOLA, fundamental frequency, phoneme duration }

{SP95-8} Y. Arai, H. Nishimura, H. Yoshida, T. Minowa, R. Mochizuki and T. Honda, 
``A study on the optimal window position to extract pitch waveforms,''
IEICE Technical Report, SP95-8, pp.53--59, May 1995.
{ pitch waveform, prosody modification, spectral distortion, sound quality evaluation, waveform concatenation }

{SP95-9} Y. Sukegawa, H. Choi, K. Maekawa and S. Sato, 
``Perception of pitch accent by Korean learners of Japanese and its implications,''
IEICE Technical Report, SP95-9, pp.61--66, May 1995.
{ prosodic features, Japanese education, accent perception, mora, moraic phonemes, syllable }

{SP95-10} J. Dang and K. Honda, 
``Acoustic effects of the pyriform fossa on vowel spectra,''
IEICE Technical Report, SP95-10, pp.1--6, May 1995.
{ vocal tract transmission characteristics, vocal tract shape, speech production, speech analysis, zeros }

{SP95-11} N. Takahashi, A. Ishida, T. Nakai and H. Suzuki, 
``Coupling of the nasal and the oral cavities based on acoustic tube model of vocal tract,''
IEICE Technical Report, SP95-11, pp.7--14, May 1995.
{ finite element method, coupling of nasal and oral cavities, nasal sound, equivalent curcuits model }

{SP95-12} C. S. Yang and H. Kasuya, 
``Individuality of vowel vocal tract shapes and normalization,''
IEICE Technical Report, SP95-12, pp.15--22, May 1995.
{ MR image, vocal tract shape, formant frequencies, individuality, vowel normalization }

{SP95-13} H. Yehia and F. Itakura, 
``Combining dynamic and acoustic constraints in the speech production inverse problem,''
IEICE Technical Report, SP95-13, pp.23--30, May 1995.
{ speech production inverse problem, formant frequency, vocal-tract cross-sectional area, singular value decomposition }

{SP95-14} K. Mori and Y. Sonoda, 
``Recognition of lip shape in articulation,''
IEICE Technical Report, SP95-14, pp.31--37, May 1995.
{ lip articulation, neural network, image processing }

{SP95-15} M. Shigenaga, T. Ogawa and M. Nakao, 
``Emotion represented by emotively uttered words,''
IEICE Technical Report, SP95-15, pp.39--46, May 1995.
{ emotion, emotively uttered word, fundamental frequency, waveform envelope }

{SP95-16} M. Abe, 
``Analysis of prosodic characteristics in speech advisories and its application to speech output,''
IEICE Technical Report, SP95-16, pp.47--54, May 1995.
{ speech synthesis-by-rule, speaking style, prosody }

{SP95-17} M. Sakata and K. Hirose, 
``Analysis and synthesis of prosodic features in spoken dialogue of Japanese,''
IEICE Technical Report, SP95-17, pp.55--62, May 1995.
{ dialogue speech, prosodic features, $F_0$contours, speech rate, spoken dialogue system }

{SP95-18} T. Beppu and K. Aikawa, 
``New time frequency masking filters for noise robust spontaneous speech recognition,''
IEICE Technical Report, SP95-18, pp.1--8, June 1995.
{ speech recognition, auditory model, dynamical feature, noise robustness, hidden Markov model }

{SP95-19} E. Tsuboka and J. Nakahashi, 
``Speeech recognition based on the Kullback-Leibler Divergence as the distance measure,''
IEICE Technical Report, SP95-19, pp.9--16, June 1995.
{ Kullback-Leibler divergence, fuzzy vector quantization, DTW, HMM }

{SP95-20} J. Yi, K. Miki and T. Yazu, 
``Study on concatenated training of subword HMMs,''
IEICE Technical Report, SP95-20, pp.17--22, June 1995.
{ HMM, subword, concatenated training, phonetic descriptions, data amount, parameters modification}

{SP95-21} Y. Komori, M. Yamada, H. Yamamoto, T. Kosaka and Y. Ohora, 
``An efficient shared-state triphone HMM using top-down clustering,''
IEICE Technical Report, SP95-21, pp.23--30, June 1995.
{ speech recognition, continuous HMM, shared-state HMM, clustering, LBG-algorithm }

{SP95-22} M. Yamada, H. Yamamoto, T. Kosaka, Y. Komori and Y. Ohora, 
``Fast output probability computation using scalar quantization and dimension independent multi-mixture computation,''
IEICE Technical Report, SP95-22, pp.31--38, June 1995.
{ speech recognition, continuous HMM, high-speed computation, scalar quantization, dimension independent multi-mixture, }

{SP95-23} T. Matsuoka, N. Uemoto, T. Matsui and S. Furui, 
``Acoustic modeling for connected digit speech recognition,''
IEICE Technical Report, SP95-23, pp.39--44, June 1995.
{ connected-digit recognition, context-dependent model, sub-word model, minimum-error training }

{SP95-24} Y. Minami and S. Furui, 
``Adaptation method using maximum likelihood procedure based on HMM composition,''
IEICE Technical Report, SP95-24, pp.45--50, June 1995.
{ HMM composition, noise, distortion, HMM adaptation }

{SP95-25} T. Murakami, K. Takeda, H. Kawai and S. Yamamoto,
``String level discriminative training of HMMs using matrix based trellis calculation,''
IEICE Technical Report, SP95-25, pp.1--7, June 1995.
{ HMM, discriminative training, trellis score, likelihood matrix }

{SP95-26} L. Zhao and S. Nakagawa,
``A Chinese continuous speech recognition system using SPOJUS-SYNO,''
IEICE Technical Report, SP95-26, pp.9--16, June 1995.
{ Chinese speech recognition system, continuous speech recognition, parsing method }

{SP95-27} J. R. Choi, H. Chung and S. Nakagawa,
``A Korean continuous speech recognition system based upon SPOJUS-SYNO,''
IEICE Technical Report, SP95-27, pp.17--24, June 1995.
{ HMM, Korean continuous speech recognition system, flight reservation task domain, SPOJUS-SYNO }

{SP95-28} S. Tagashira, M. Nishijima and Y. Ariki,
``Speaker recognition and speaker normalization by projection to speaker subspace,''
IEICE Technical Report, SP95-28, pp.25--32, June 1995.
{ speaker recognition, phoneme recognition, subspace method, singular value decomposition, CLAFIC, principal component analysis, canonical correlation analysis }

{SP95-29} H. K. Kwan and K. Hirose,
``Use of phoneme-based features in language identification,''
IEICE Technical Report, SP95-29, pp.33--40, June 1995.
{ unigram, bigram, parallel phoneme recognition, mixed phoneme recognition, channel normalization }

{SP95-30} Y. Wakita, S. Harald and Y. Sagisaka,
``Phoneme candidate re-entry modeling using recognition error characteristics over multiple HMM states,''
IEICE Technical Report, SP95-30, pp.41--47, June 1995.
{ speech recognition, phoneme candidates re-entry modeling, error characteristics, speaker adaptation, Context Sensitive Smoothing(CSS) }

{SP95-31} Y. Niimi, K. Takahashi and Y. Kobayashi,
``Detection of misrecognition and out-of-vocabulary word intervals in speech recognition,''
IEICE Technical Report, SP95-31, pp.49--56, June 1995.
{ misrecognition, out-of-vocabulary words, posterior probability }

{SP95-32} H. Murakami,
``Frame synchronous full search algorithm and applied for spontaneous speech recognition,''
IEICE Technical Report, SP95-32, pp.57--64, June 1995.
{ spontaneous speech recognition, full search, beam search, frame synchronous, garbage model, word trigram model }

{SP95-33} M. Suzuki, S. Makino and H. Aso,
``Application of discrete-type HMnet to language models,''
IEICE Technical Report, SP95-33, pp.65--72, June 1995.
{ descrete-type HMnet, NL-HMnet, successive state splitting, language models }

{SP95-34} Y. Itoh, J. Kiyama, H. Kojima, S. Seki and R. Oka,
``Reference interval-free continuous dynamic programming(RIFCDP) for spotting speech waves by arbitrary parts of a reference pattern,''
IEICE Technical Report, SP95-34, pp.73--80, June 1995.
{ spotting, continuous DP, same section detection, reference pattern acquisition, location detection }

{SP95-35} J. Kiyama, Y. Itoh and R. Oka,
``Domain independent speech summary using incremental reference interval-free continuous dynamic programming,''
IEICE Technical Report, SP95-35, pp.81--88, June 1995.
{ speech summary, similar section extraction, topic boundary detection, topic independence }

{SP95-36} M. Tamoto and T. Kawabata,
``Investigation of cooperative tasks for dialogue data collection,''
IEICE Technical Report, SP95-36, pp.89--94, June 1995.
{ speech understanding, natural language processing, speech dialogue database, JUNO }

{SP95-37} T. Kitamura, N. Takagi and M. Akagi,
``Freqency bands having speaker individualities,''
IEICE Technical Report, SP95-37, pp.1--6, July 1995.
{ speaker individualities, spectral envelopes, spectral distance, ABX test }

{SP95-38} T. Kawahara, H. Ogawa and S. Doshita,
``Subjective evaluation of voice quality--- relation between psychological similarity and acoustic similarity---,''
IEICE Technical Report, SP95-38, pp.7--13, July 1995..  
{ voice quality, semantic differential method, multi-dimensional scaling method, speaker identification, `Kansei' information processing }

{SP95-39} S. Okawa and K. Shirai,
``Speaker adaptive speech recognition by semi-continuous SPC-HMM,''
IEICE Technical Report, SP95-39, pp.15--22, July 1995.    
{ phoneme recognition, word recognition, statistical phoneme center, SPC-HMM, semi-continuous HMM, speaker adaptation }

{SP95-40} T. Irino,
``A computational theory of the peripheral auditory system,''
IEICE Technical Report, SP95-40, pp.23--30, July 1995.  
{ computational theory, auditory filter, scale representation, minimal uncertainty, event detection, early vision }

{SP95-41} H. Miyabayashi and T. Funada,
``Study on the effect of feedback loops and cross-coupled hidden layers in NN for pitch extraction,''
IEICE Technical Report, SP95-41, pp.31--38, July 1995.  
{ pitch extraction, neural network, feedback, cross-coupling, time-continuity, smooth fluctuation }

{SP95-42} K. Aikawa and  M. Tsuzaki,
``Aftereffect on the perception of frequency-modulated tones,''
IEICE Technical Report, SP95-42, pp.1--8, July 1995.
{ sweep tone, FM tone, auditory perception, pitch tracking, aftereffect }

{SP95-43} K. Kurakata, M. Matsui and A. Nishimura,
``Perceptual trajectory of the continuity effect of frequency glide(second report),''
IEICE Technical Report, SP95-43, pp.9--16, July 1995.
{ auditory scene analysis, continuity effect, drawing method, perceptual trajectory, prediction of frequency change }

{SP95-44} M. Matsui, K. Kurakata and A. Nishimura,
``Psychological processes of prediction and constraints in auditory scene analysis,''
IEICE Technical Report, SP95-44, pp.17--24, July 1995.
{ auditory scene analysis, perceptual trajectory, prediction, self-generation, constraints }

{SP95-45} M. Tsuzaki and H. Kato,
``Shrinking of perceived duration by acoustic interruption---effects of temporal position and "continuity"---,''
IEICE Technical Report, SP95-45, pp.25--30, July 1995.
{ perceived duration, auditory object, continuity, shrinking illusion, stream segregation, auditory induction }

{SP95-46} S. Amano,
``Time-course of phoneme/word perception in Japanese,''
IEICE Technical Report, SP95-46, pp.31--38, July 1995.
{ phoneme, word, time-modification, perception, reaction time }

{SP95-47} K. Itoh and M. Mizushima,
``Influence of waveform envelope modification on speech perception,''
IEICE Technical Report, SP95-47, pp.39--45, July 1995.
{ speech waveform envelope, normal and hearing impaired person, hearing aid, speech power control, frame by frame processing }

{SP95-48} H. Baba and M. Ebata,
``Survey of ambulance-siren on consciousness of the crew,''
IEICE Technical Report, SP95-48, pp.47--53, July 1995.
{ ambulance, electronic siren, questionnaire, crew, health }

{SP95-49} K. Koishida, K. Tokuda, T. Kobayashi and S. Imai,
``Spectral representation of speech using mel-generalized cepstrum and its properties,''
IEICE Technical Report, SP95-49, pp.1--8, Sept. 1995.
{ mel-generalized cepstrum, mel-generalized cepstral analysis, spectral quantization }

{SP95-50} M. Kihata,
``A new method of coding LSP coefficients using recurrent neural networks,''
IEICE Technical Report, SP95-50, pp.9--16, Sept. 1995.
{ recurrent neural network, LSP coefficient, speech coding, BPTT training, interpolation }

{SP95-51} K. Koishida, K. Tokuda, T. Kobayashi and S. Imai,
``CELP coder based on mel-generalized cepstral analysis ,''
IEICE Technical Report, SP95-51, pp.17--24, Sept. 1995.
{ mel-cepstrum, mel-cepstral analysis, characteristics auditory sensation, CELP }

{SP95-52} H. Sono and T. Funada,
``Vector quantization of LSP parameters with three-layer neural networks and investigation by listening test,''
IEICE Technical Report, SP95-52, pp.25--32, Sept. 1995.
{ LSP parameter, vector quantization, layer neural network }

{SP95-53} T. Kitamura and S. Takei,
``Speaker identification using dynamic features of speech and feature map,''
IEICE Technical Report, SP95-53, pp.33--39, Sept. 1995.
{ speaker identification, feature map, predictive network, text independent }

{SP95-54} M. Goto, K. Takeda and F. Itakura,
``On the robustness of speaker identification to speaking styles,''
IEICE Technical Report, SP95-54, pp.41--46, Sept. 1995.   
{ speaker identification, VQ codebook, speaking style }

{SP95-55} H. Kohda and T. Kitamura,
``Noise reduction using neural network and regression analysis,''
IEICE Technical Report, SP95-55, pp.1--5, Sept. 1995.
{ regressive analysis, noise reduction, neural network }

{SP95-56} A. Wakao, K. Takeda and F. Itakura,
`Normalizing Lombard speech under different noise conditions,''
IEICE Technical Report, SP95-56, pp.7--14, Sept. 1995.
{ Lombard effect, adaptation, DTW recognizer }

{SP95-57} Y. Mori and N. Aikawa,
``Japanese vowels recognition using principal component analysis,''
IEICE Technical Report, SP95-57, pp.15--20, Sept. 1995.
{ vowel recognition, speaker-independent speech recognition, principal component analysis }

{SP95-58} M. Nakano, T. Nakanishi, I. Takumi, M. Hata and K. Yamada,
``Improving convergence speed of pole argument control on IIR-ADF for line canceler,''
IEICE Technical Report, SP95-58, pp.21--28, Sept. 1995.
{ line canceler, adaptive digital filter, pole angle control }

{SP95-59} T. Nakanishi, I. Takumi and M. Hata,
``Implementation of IIR ADF for narrow band noise elimination by using of DSP,''
IEICE Technical Report, SP95-59, pp.29--36, Sept. 1995.
{ IIR filter, ADF, NLMS }

{SP95-60} P. Zavarsky and N. Fujii,
``Inconsistent estimates of local moment functions and related problems,''
IEICE Technical Report, SP95-60, pp.37--44, Sept. 1995.
{ nonstationary signal, time-frequency distribution, crossterms, cross-frequency-ambiguity domain }

{SP95-61} T. Hirano, T. Sato and A. Noda,
``Exponential smoothing method with refractory for inhomogenious-interval data,''
IEICE Technical Report, SP95-61, pp.45--52, Sept. 1995.
{ refractory, inhomogenious-interval discrete-time data, exponential smoothing method, data drop }

{SP95-62} M. Tanaka, 
``Microphone array signal processing techniques,''
IEICE Technical Report, SP95-62, pp.1--8, Oct. 1995.
{ microphone array, high-quality sound receiving, adaptive array, direction estimation }
 
{SP95-63} S. Ise,
``Theory of the sound field reproduction based on the multi-channel signal processing,''
IEICE Technical Report, SP95-63, pp.9--17, Oct. 1995.
{ sound field reproduction, active noise control, multi-channel signal processing }

{SP95-64} K. Loken-Kim, S. Mizunashi and T. Morimoto,
``ATR's multimodal interpreting telecommunications:implementation of multimodal user interface,''
IEICE Technical Report, SP95-64, pp.19--26, Oct. 1995.
{ multimodal interaction, spoken language interpretation }

{SP95-65} T. Yamada, S. Nakamura and K. Sikano,
``Speech Recognition with speaker localization by microphone array,''
IEICE Technical Report, SP95-65, pp.27--34, Oct. 1995.
{ speech recognition, noise environment, microphone array, source localization, man-machine interface }

{SP95-66} K. Aikawa and H. Kawahara,
``A neural network model for tracking frequency-modulated tones,''
IEICE Technical Report, SP95-66, pp.1--8, Oct. 1995.
{ FM tone, neural network, dynamic characteristics, tracking }

{SP95-67} T. Moriyama, H. Saito and S. Ozawa,
``Evaluation of correspondence between emotional concept and emotional parameter on speech,''
IEICE Technical Report, SP95-67, pp.9--16, Oct. 1995.
{ vocal emotion, factor analysis, principal component analysis, multiple regression analysis }

{SP95-68} S. Hayakawa, K. Takeda and F. Itakura,
``Text-independent speaker recognition using the higher frequency band,''
IEICE Technical Report, SP95-68, pp.17--24, Oct. 1995.
{ speaker recognition, higher frequency band, period between reference and test utterances, transitional feature, cross-sex confusion }

{SP95-69} T. Sano, E. Hirata and T. Iwasaki,
``Field testing of a telephone communication system for operation of electric power equipment,''
IEICE Technical Report, SP95-69, pp.25--32, Oct. 1995.
{ speech interface, speech dialogue, field testing, telephone, electric power system }

{SP95-70} S. Homma, J. Takahashi and S. Sagayama,
``Iterative unsupervised speaker adaptation for batch dictation,''
IEICE Technical Report, SP95-70, pp.33--40, Oct. 1995.
{ batch dictation, unsupervised speaker adaptation }

{SP95-71} T. Takiguchi, S. Nakamura and K. Shikano,
``Speech recognition in additive noise and room acoustics distortion by HMM composition,''
IEICE Technical Report, SP95-71, pp.41--46, Oct. 1995.
{ background noise, room acoustics distortion, HMM composition }

{SP95-72} J. Kiyama, Y. Itoh and S. Seki and R. Oka,
``Common segment pair detection using statistical approach for speech summary,''
IEICE Technical Report, SP95-72, pp.47--54, Oct. 1995.
{ speech summary, similar section detection, repetition interval, statistical approach }

{SP95-73} H. Masataki, S. Matsunaga and Y. Sagisaka,
``Variable-order statistical language modeling for continuous speech recognition,''
IEICE Technical Report, SP95-73, pp.1--6, Nov. 1995.
{ continuous speech recognition, statistical language modeling, N-gram, perplexity }

{SP95-74} T. Kobayashi,
``ALICE:Acquisition of language in conversational environment---an approach to weakly supervised training of spoken language system for language porting---,''
IEICE Technical Report, SP95-74, pp.7--14, Nov. 1995.
{ language acquisition, language porting, spoken language system }

{SP95-75} M. Endo, T. Ito, M. Hoshimi and K. Niyada,
``A study of language modeling for speech recognition using co-occurent word model,''
IEICE Technical Report, SP95-75, pp.15--22, Nov. 1995.
{ speech recognition, language modeling, word n-gram model, co-occurent word model }

{SP95-76} H. Sakamoto and S. Matsunaga,
``On detection of unregistered-words using phoneme cluster models,''
IEICE Technical Report, SP95-76, pp.23--30, Nov. 1995.
{ continuous speech recognition, phoneme cluster model, n-grams, unregistered-word }

{SP95-77} M. Takano, K. Iso and T. Watanabe,
``A word recognition using demi-syllable wordspotting,''
IEICE Technical Report, SP95-77, pp.31--38, Nov. 1995.
{ word recognition, non-keyword, robustness, wordspotting, likelihood normalization, inhibition for overlapped word detection }

{SP95-78} H. Ohmura,
``Intensity envelope controlled speech synthesis for considering a nonlinearity deu to the vocal folds vibration,''
IEICE Technical Report, SP95-78, pp.39--46, Nov. 1995.
{ vibration of vocal folds, nonlinearity, intensity envelope, speech synthesis }

{SP95-79} T. Abe, T. Kobayashi and S. Imai,
``Pitch estimation based on instantaneous frequency in noisy environments,''
IEICE Technical Report, SP95-79, pp.47--54, Nov. 1995.
{ instantaneous frequency, speech enhancement, pitch estimation }

{SP95-80} T. Morii, N. Tanaka and K. Yoshida,
``Multi-mode CELP codec using short-term characteristics of speech,''
IEICE Technical Report, SP95-80, pp.55--62, Nov. 1995.
{ CELP, variable rate codec, multi-mode codec, neural networks }

{SP95-81} M. Tamoto and  T. Kawabata,
``Investigation of cooperative task dialogue,''
IEICE Technical Report, SP95-81, pp.1--6, Dec. 1995.
{ speech understanding, natural language processing, speech dialogue database, JUNO }

{SP95-82} A. Sakurai and K. Hirose,
``Searching phrase boundaries by the method of partial AbS of fundamental frequency contours,''
IEICE Technical Report, SP95-82, pp.7--12, Dec. 1995.
{ fundamental frequency contours, $F_0$ model, partial AbS, phrase boundaries }

{SP95-83} M. Kawamori, T. Kawabata and A. Shimazu,
``A phonological study on Japanese discourse markers(II),''
IEICE Technical Report, SP95-83, pp.13--20, Dec. 1995.
{ dialogue understanding, discourse markers, intonation, phonology }

{SP95-84} M. Sakuta, Y. Yamashita and R. Mizoguchi,
``To generate various expressions of the surface sentence and the prosody in a dialog,''
IEICE Technical Report, SP95-84, pp.21--28, Dec. 1995.
{ spoken dialog, dialog context, dialog feature, fundamental frequency, speech synthesis }

{SP95-85} H. Kamio, M. Amamiya, A. Uchiyama, H. Matsuura and T. Nitta,
``The development of rapid prototyping tool "Muse" for social information systems,''
IEICE Technical Report, SP95-85, pp.29--34, Dec. 1995.
{ usr interface, multimodal interface, GUI, object oriented }

{SP95-86} H. G. Okuno, T. Nakatani and T. Kawabata,
``Evaluation of sound stream segregation from the viewpoint of speech recognition,''
IEICE Technical Report, SP95-86, pp.35--40, Dec. 1995.
{ computational auditory scene analysis, sound stream segregation, speech understanding, spectrum distortion }

{SP95-87} L. Fais and K. Loken-Kim,
``How many words is a picture really worth?,''
IEICE Technical Report, SP95-87, pp. 41--47, Dec. 1995.
{ multimedia, interpreted conversation, meta-conversation, automatic translation system }
 
{SP95-88} T. Shimizu, H. Yamamoto, S. Matsunaga and Y. Sagisaka,
``Spontaneous dialogue speech recognition using cross-word context constrained word graph,''
IEICE Technical Report, SP95-88, pp.49--54, Dec. 1995.
{ continuous speech recognition, search method, word graph, lexicon tree }

{SP95-89} T. Takezawa and T. Morimoto,
``Continuous speech recognition using a grammar based on subtrees and preterminal bigrams,''
IEICE Technical Report, SP95-89, pp.55--62, Dec. 1995.
{ continuous speech recognition, spoken language processing, integrated processing of speech and language, syntactic rules, partial trees, stochastic language modeling }

{SP95-90} K. Ohtsuki, T. Mori, T. Matsuoka, S. Furui and K. Shirai,
``Study of large-vocabulary continuous speech recognition using read-speech corpus,''
IEICE Technical Report, SP95-90, pp.63--68, Dec. 1995.
{ continuous speech recognition, large vocabulary, speech corpus }

{SP95-91} P. A. Heeman and K. Loken-Kim,
``Using structural information to detect speech repairs,''
IEICE Technical Report, SP95-91, pp.69--76, Dec. 1995.
{ speech dysfluencies, spoken dialog processing }

{SP95-92} M. Ishizaki, Y. Den, S. Tuchiya, S. Tamoto and S. Nakazato,
``Classification of task-oriented dialogue,''
IEICE Technical Report, SP95-92, pp.77--85, Dec. 1995.
{ dialogue corpus, task-oriented dialogue, planning }

{SP95-93} T. Kawabata and M. Tamoto,
``Back-off method for N-gram smoothing based on binomial posteriori distribution,''
IEICE Technical Report, SP95-93, pp.1--6, Dec. 1995.
{ Natural language, n-gram, back-off, JUNO }

{SP95-94} T. Matsuoka, R. Hasson, M. Barlow and S. Furui,
``Language model acquisition from a text corpus for speech understanding,''
IEICE Technical Report, SP95-94, pp.7--12, Dec. 1995.
{ speech understanding, translation, language modeling, natural language, semantic language }

{SP95-95} K. Ohtani and S. Nakagawa,
``A semi-automatic learning method of grammar rules by the combination of CFG and bigram,''
IEICE Technical Report, SP95-95, pp.13--18, Dec. 1995.
{ learning of grammar, CFG, word pair, coverage, perplexity }

{SP95-96} A. Ito and M. Kohda,
``Language modelling by string pattern n-gram,''
IEICE Technical Report, SP95-96, pp.19--24, Dec. 1995.
{ language model, n-gram, word similarity }

{SP95-97} R. Matsumura and T. Okamoto,
``Comparative verification of features for text-independent speaker recognition,''
IEICE Technical Report, SP95-97, pp.25--30, Dec. 1995.

{SP95-98} S. Tagashira and Y. Ariki,
``Speaker-independent HMM through speaker normalization by projection to subspace,''
IEICE Technical Report, SP95-98, pp.31--38, Dec. 1995.
{ speaker-independent HMM, subspace method, CLAFIC canonical correlation analysis }

{SP95-99} M. Yamada, Y. Ohno, M. Hoshimi and K. Niyada,
``A study of speaker independent speech recognition method with constrained time alignment near phoneme discriminative frame,''
IEICE Technical Report, SP95-99, pp.39--44, Dec. 1995.
{ speaker independent speech recognition, discriminative frame }

{SP95-100} K. Takagi, K. Shinoda, H. Hattori and T. Watanabe,
``Robust speaker adaptation effective for environmental charges,''
IEICE Technical Report, SP95-100, pp.45--52, Dec. 1995.
{ speech recognition, speaker adaptation, environment adaptation, unsupervised adaptation, incremental adaptation }

{SP95-101} K. Ozeki,
``The mutual information as a scoring function for speech recognition,''
IEICE Technical Report, SP95-101, pp.53--60, Dec. 1995.
{ mutual information, likelihood, normalization of likelihood, ergodic HMM, allphone model, word-spotting }

{SP95-102} S. Takahashi and S. Sagayama,
``Tied structure for acoustic models based on transfer vector correlations,''
IEICE Technical Report, SP95-102, pp.61--68, Dec. 1995.
{ speech recognition, speaker adaptation, HMM, tied structure, phoneme model }

{SP95-103} J. Takahashi and S. Sagayama,
``An efficient minimum classification error training for a small amount of data,''
IEICE Technical Report, SP95-103, pp.69--76, Dec. 1995.
{ speech recognition, HMM, minimum classification error training, MCE, maximum a posteriori estimation, Bayesian learning, transfer vector field smoothing, speaker adaptation }

{SP95-104} K. Yamamoto and S. Nakagawa,
``Segmental unit input HMM and its evaluation,''
IEICE Technical Report, SP95-104, pp.77--84, Dec. 1995.
{ speech recognition, HMM, dynamic features, segmental statistics }

{SP95-105} D. Kobayashi, S. Kajita, K. Takeda and F. Itakura,
``Extracting speech features from human speech-like noise,''
IEICE Technical Report, SP95-105, pp.85--92, Dec. 1995.
{ human speech-like noise, speech detection, amplitude distribution of signal, source-filter model }

{SP95-106} H. Kojima and K. Tanaka,
``Automatic generation of word models using piecewise linear segment lattices,''
IEICE Technical Report, SP95-106, pp.93--98, Dec. 1995.
{ word model, piecewise linear lattice, formation of phonological concepts }

{SP95-107} A. Nakamura,
``A garbage model training for word spotter with artificially generated training data,''
IEICE Technical Report, SP95-107, pp.99--104, Dec. 1995.
{ word spotting, garbage model, minimum error training, artificially generated training data }

{SP95-108} Y. Yonezawa and M. Akagi,
``Word spotting using a contextual effect model,''
IEICE Technical Report, SP95-108, pp.105--110, Dec. 1995.
{ word spotting, continuous dynamic programming, contextual effect, coarticulation }

{SP95-109} M. Honda,
``Modelling and analysis of speech dynamics,''
IEICE Technical Report, SP95-109, pp.1--8, Jan. 1996.
{ speech signal model, data compression, speech production, dynamic model }

{SP95-110} K. Ozawa,
``Speech coding technologies and their practical applications,''
IEICE Technical Report, SP95-110, pp.9--16, Jan. 1996.
{ speech coding, ADPCM, MP-LPC, CELP, wireless and wireline applications }

{SP95-111} T. Matsui,
``HMM-based speaker recognition,''
IEICE Technical Report, SP95-111, pp.17--24, Jan. 1996.
{ speaker recognition, speaker verification, hidden Markov model, text-dependent, text-independent, text-prompted }

{SP95-112} H. Sakakibara, T. Nakai and H.Suzuki,
``Analysis of acoustic sound propagation in the nasal tract by 3-D FEM modeling,''
IEICE Technical Report, SP95-112, pp.25--32, Jan. 1996.
{ nasal caving, MR image, 3D acoustic tube, finite elements method }

{SP95-113} H. Matsuzaki, N. Miki and Y. Ogawa,
``A study on elliptic sound tube model of vocal tract with volume of radiation using 3-D FEM,''
IEICE Technical Report, SP95-113, pp.33--38, Jan. 1996.
{ 3-D FEM, vocal tract ellipec sound tube model, radiation impedance, volume radiation }

{SP95-114} T. Someya, N. Miki, K.Motoki and Y. Ogawa,
``Measurement of the surface roughness of tongue and measurement of propagation constant of sound tube with roughness,''
IEICE Technical Report, SP95-114, pp.39--44, Jan. 1996.
{ attenuation constant, plaster replica, surface roughness, sound tube with roughness }

{SP95-115} K. Mori and Y. Sonoda,
``Relationship between lip shapes and acoustical characteristics during speech,''
IEICE Technical Report, SP95-115, pp.45--52, Jan. 1996.
{ lip articulation, neural network, acoustical characteristics, formant, image processing }

{SP95-116} N. Miki,
``Vocal tract transfer function of vowels depended on vocal sources,''
IEICE Technical Report, SP95-116, pp.53--58, Jan. 1996.
{ vocal tract model, glottis model, turbulent source }

{SP95-117} K. Itou, S. Hayamizu and K.Tanaka,
``A timing management method for integrated dialog systems,''
IEICE Technical Report, SP95-117, pp.1--6, Jan. 1996.
{ integration, timing, dialog system, server }

{SP95-118} N. Inoue, M. Nakamura and S. Sakayori,
``The fast speech recognition method by checking likelihood of word unique cells in tree grammars,''
IEICE Technical Report, SP95-118, pp.7--12, Jan. 1996.
{ speech recognition, tree search, word unique cell, fast recognition method }

{SP95-119} H. Hattori and E. Yamada,
``Speech recognition using context-dependent demi-syllable units,''
IEICE Technical Report, SP95-119, pp.13--20, Jan. 1996.
{ speech recognition, phonetic context, context-dependent model, demi-syllable }

{SP95-120} T. Matsui, T. Nishitani and S. Furui,
``A study of model and a priori threshold updating in speaker verification,''
IEICE Technical Report, SP95-120, pp.21--26, Jan. 1996.
{ speaker verification, model updating, a priori threshold, hidden Markov model, text-independent }

{SP95-121} M. Morishima, T. Isobe, F. Yoshitani and N. Koizumi,
``Evaluation of voice-activated banking system in telephone network,''
IEICE Technical Report, SP95-121, pp.27--33, Jan. 1996.
{ speech recognition, telephone speech, home banking, field trial, questionnaire }

{SP95-122} K. Tokuda, T. Masuko, T. Kobayashi and S. Imai,
``A speech parameter generation algorithm based on HMM,''
IEICE Technical Report, SP95-122, pp.35--42, Jan. 1996.
{ speech synthesis, hidden Markov model, mel-cepstrum, MLSA filter, }

{SP95-123} T. Masuko, K. Tokuda, T. Kobayashi and S. Imai,
``Speech synthesis using HMMs based on mel-cepstral representation,''
IEICE Technical Report, SP95-123, pp.43--50, Jan. 1996.
{ speech synthesis, hidden Markov model, mel-cepstral analysis, MLSA filter, }

{SP95-124} J. Shimizu, Y. Miyanaga and K. Tochinai,
``Speech enhancement using a robust adaptive total least squares algorithm,''
IEICE Technical Report, SP95-124, pp.51--58, Jan. 1996.
{ speech enhancement, Kalman filtering, robust estimation, total least squares algorithm, EM algorithm, white Gaussian noise, impulse noise }

{SP95-125} K. Sasaki, N. Miki and Y. Ogawa,
``A note on formant estimation of vocal production with a vocal source model including noises,''
IEICE Technical Report, SP95-125, pp.59--66, Jan. 1996.
{ noises, vocal source model, synthesis model, TLS-method }

{SP95-126} T. Watanabe,
``Reaction time of discrimination between target and nontarget words,''
IEICE Technical Report, SP95-126, pp.67--74, Jan. 1996.
{ reaction time, word, discrimination, speech menu, the visually impaired and blind, Windows }

{SP95-127} H. Imai, Y. Miyanaga and K. Tochinai,
``On spectrum estimation using non-linear network controlling error variance,''
IEICE Technical Report, SP95-127, pp.75--81, Jan. 1996.
{ non-linear network, supervised clustering, high speed learning, non-linear spectrum estimation }

{SP95-128} Y. Shiraki,
``Deformation of speech-spectrum and surgery theory,''
IEICE Technical Report, SP95-128, pp.83--90, Jan. 1996.
{ deformation of speech-spectrum, speaker adaptation, surgery theory, topological field theory }

{SP95-129} J. Miwa and D. Fryantoni,
``Estimation of formant and anti-formant of pole-zero speech using analysis-by-synthesis techniques,''
IEICE Technical Report, SP95-129, pp.1--8, Feb. 1996.
{ speech analysis, pole and zero, analysis-by-synthesis, nasal, anti-formant }

{SP95-130} N. Osaka,
``A timbre interpolation using a sinusoidal model,''
IEICE Technical Report, SP95-130, pp.9--16, Feb. 1996.
{ sinusoidal model, timbre interpolation, morphing, DP, similarity test, MNRU }

{SP95-131} T. Yonezaki and K. Shikano,
``Robust entropy coded vector quantization with hidden Markov models,''
IEICE Technical Report, SP95-131, pp.17--24, Feb. 1996.
{ speech coding, vector quantization, HMMs, entropy coding, robustness }

{SP95-132} M. Saito, M. Masukata and S. Nakagawa,
``Automatic acquisition of speech units for ultra very low bit coding,''
IEICE Technical Report, SP95-132, pp.25--32, Feb. 1996.
{ ultra very low bit coding, automatic acquisition of speech units, speech recognition }

{SP95-133} R. Matsumura and Toshio Okamoto,
``Text-independent speaker identification using pitch information,''
IEICE Technical Report, SP95-133, pp.33--40, Feb. 1996.
{ speaker identification, pitch information, text-independent, discriminant function }

{SP95-134} N. Minematsu, S. Kusakari, S. Nakagawa and K. Hirose,
``Development of a speech stimuli generation system for perceptual experiments,''
IEICE Technical Report, SP95-134, pp.41--48, Feb. 1996.
{ speech perception, analysis re-synthesis, LMA filter, prosodic features, human-likeness }

{SP95-135} S. Imaizumi, K. Mori, S. Kiritani, M. Yumoto, H. Seki and K. Yamaki,
``Magnetoencephalographic observation of audio-visual integration,''
IEICE Technical Report, SP95-135, pp.1--6, March 1996.
{ MEG, audio-visual integration, McGurk effect, mismatch magnetic field(MMF), dipole model }

{SP95-136} K. Aikawa and M. Tsuzaki,
``On the characteristics of dynamic perception of various frequency-modulated tones,''
IEICE Technical Report, SP95-136, pp.7--14, March 1996.
{ FM tone, sweep tone, dynamic characteristics, tracking, pure tone sequence }

{SP95-137} N. Aoki and T. Ifukube,
``Naturalness of synthetic voice resulting from amplitude fluctuation of the source signal,''
IEICE Technical Report, SP95-137, pp.15--21, March 1996.
{ speech synthesis, artificial larynx, buzz, Rosenberg wave, $1/f^¥delta$ fluctuation }

{SP95-138} O. Wada, K. Ozawa, Y. Suzuki, T. Sone, T. Kawase and T. Takasaka,
``A consideration on binaural fitting of a loudness compensation hearing aid,''
IEICE Technical Report, SP95-138, pp.23--30, March 1996.
{ loudness compensation, binaural hearing, sensorineurally hearing-impairment }

{SP95-139} T. Hagiwara, Y. Yonezawa and M. Akagi,
``A relation between contextual effects and phonemic quality of vowels,''
IEICE Technical Report, SP95-139, pp.31--38, March 1996.
{ contextual effect, vowel perception, phonemic quality, overshoot, anchor }

{SP95-140} H. Konno, J. Toyama, M. Shimbo and K. Murata,
``The effect of formant frequency and spectral tilt of unvoiced vowels on their perceived pitch and phonemic quality,''
IEICE Technical Report, SP95-140, pp.39--45, March 1996.
{ unvoiced vowel, pitch, phonemic quality, spectral tilt, formant frequency, paired comparison }

{SP95-141} Y. Kitamura, M. Iwaki and T. Iijima,
``Pluralizing method of similarity for speaker-independent vowel recognition,''
IEICE Technical Report, SP95-141, pp.47--54, March 1996.
{ natural observation method, pluralized simple similarity, characteristic of vowel }

{SP95-142} T.Mori, M.Iwaki and T.Iijima,
``On a vowel synthesis system using natural observation method,''
IEICE Technical Report, SP95-142, pp.1--8, March 1996.
{ speech synthesis, sound source wave, finite dirichlet series, natural observation filter }

{SP95-143} T. Mori, M. Abe and K. Shirai,
``Voice conversion by non-parametric transformation of band-divided spectral envelope,''
IEICE Technical Report, SP95-143, pp.9--16, March 1996.
{ speech synthesis, voice conversion, spectral envelope, formant frequency, band-division }

{SP95-144} T. Kitamura and M. Akagi,
``Significant physical cues for speaker identification in speech spectral envelopes,''
IEICE Technical Report, SP95-144, pp.17--24, March 1996.
{ speaker identification, speaker individuality, spectral envelopes, voice quality control }

{SP95-145} K. Ashihara and S. Sato,
``Noise reduction achieved by estimation of the cepstrum lifter based on linear prediction in frequency domain,''
IEICE Technical Report, SP95-145, pp.25--30, March 1996.
{ noise reduction, cepstrum lifter, sylabic intelligibility, linear prediction }

{SP95-146} N. Takahashi, T. Nakai and H. Suzuki,
``A study of the effects of the 3-D vocal tract shape using finite element method,''
IEICE Technical Report, SP95-146, pp.31--36, March 1996.
{ finite element method, bend tube, vocal tract with the velum, vocal tract wall impedance }

{SP95-147} T. Takagi, N. Seiyama and E. Miyasaka,
``A pitch extraction method with multiple window-lengths for real-time speech processing,''
IEICE Technical Report, SP95-147, pp.37--44, March 1996.
{ pith extraction, autocorrelation, multiple window-lengths, real-time processing, pitch modification, speech rate conversion }

{SP95-148} K. Nishi, M. Abe and S. Ando,
``Multiple speech segregation by using the optimum harmonics tracking filter,''
IEICE Technical Report, SP95-148, pp.45--52, March 1996.
{ auditory scene analysis, harmonics tracking, wavelet analysis, pitch estimation }

{SP95-149} H. Kato, M. Tsuzaki and Y. Sagisaka,
``Acceptability for temporal modification of two consecutive segments in words,''
IEICE Technical Report, SP95-149, pp.53--60, March 1996.
{ speech perception, time perception, durational rules, objective evaluation of synthetic rules }

{SP95-150} Y. Ishikawa and K. Nakajima,
``Duration rules based on two morae units for Japanese text-to-speech system,''
IEICE Technical Report, SP92-150, pp.61--68, March 1996.
{ speech synthesis, prosody, duration control, perception of rhythm }

{SP95-151} S. Morimoto and K. Kakehi,
``Counting moras in Japanese speech by a neural network,''
IEICE Technical Report, SP95-151, pp.69--76, March 1996.
{ onset-sensitive auditory neuron model, neural network, counting moras, speaking rate }