NDLI: Likelihood normalization using an ergodic HMM for continuous speech recognition

Please wait, while we are loading the content...

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

Volume 4 - 1996

Channel and noise normalization using affine transformed cepstrum

Spectral estimation and normalisation for robust speech recognition

Trellis encoded vector quantization for robust speech recognition

Phone clustering using the Bhattacharyya distance

Variability of Lombard effects under different noise conditions

Lombard effect compensation and noise suppression for noisy Lombard speech recognition

The use of shibboleth words for automatically classifying speakers by dialect

Data collection of Japanese dialects and its influence into speech recognition

Statistical dialect classification based on mean phonetic features

Norwegian numerals: a challenge to automatic speech recognition

Evaluation of the Telefonica I+D Natural Numbers Recognizer over different dialects of Spanish from Spain and America

Rhythmic constraints on English stress timing

On the interaction of clash, focus and phonological phrasing

On the quantal nature of speech timing

Differential perception of tonal contours through the syllable

Pitch, loudness, and segmental duration correlates: towards a model for the phonetic aspects of Finnish prosody

Prosodic manipulation system of speech material for perceptual experiments

Clustered language models with context-equivalent states

Modeling of contextual effects and its application to word spotting

A new keyword spotting algorithm with pre-calculated optimal thresholds

Detection of ambiguous portions of signal corresponding to OOV words or misrecognized portions of input

Techniques for approximating a trigram language model

Unsupervised and incremental speaker adaptation under adverse environmental conditions

An adaptive-beam pruning technique for continuous speech recognition

Data based filter design for RASTA-like channel normalization in ASR

A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition

Language-model look-ahead for large vocabulary speech recognition

A new search algorithm in segmentation lattices of speech signals

LR-parser-driven Viterbi search with hypotheses merging mechanism using context-dependent phone models

Discrete-utterance recognition with a fast match based on total data reduction

On-line garbage modeling with discriminant analysis for utterance verification

Cheating with imperfect transcripts

Novel training method for classifiers used in speaker adaptation

Large vocabulary word recognition based on a graph-structured dictionary

A word graph based N-best search in continuous speech recognition

Viterbi beam search with layered bigrams

A wave decoder for continuous speech recognition

Long term on-line speaker adaptation for large vocabulary dictation

Incremental generation of word graphs

Improvement in N-best search for continuous speech recognition

Sethos: the UPC speech understanding system

Segmental search for continuous speech recognition

An investigation into the generation of mouth shapes for a talking head

A text-to-audiovisual-speech synthesizer for French

Analysis of head movements and its role in spoken dialogue

RWC multimodal database for interactions by integration of spoken language and visual information

About the relationship between eyebrow movements and Fo variations

How many words is a picture really worth?

Visual synthesis of source acoustic speech through Kohonen neural networks

Audio-visual speech perception without speech cues

Multilingual speech recognition at Dragon Systems

Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds

Japanese speech databases for robust speech recognition

Spoken language processing in a multilingual context

Multilingual human-computer interactions: from information access to language learning

SpeeData: multilingual spoken data entry

Pseudo-articulatory representations in speech synthesis and recognition

Synthesis of initial (/s/-) stop-liquid clusters using HLsyn

Synthesis of trill

Phone-based speech synthesis with neural network and articulatory control

Analysis of ten vowel sounds across gender and regional/cultural accent

Speech morphing by gradually changing spectrum parameter and fundamental frequency

The multi-lag-window method for robust extended-range F/sub 0/ determination

Nonlinear estimation of DEGG signals with applications to speech pitch detection

Pitch analysis methods for cross-speaker comparison

Continuous adaptation of linear models with impulsive excitation

Quantitative analysis of the local speech rate and its application to speech synthesis

A fast and reliable rate of speech detector

Context modeling and clustering in continuous speech recognition

Hierarchical partition of the articulatory state space for overlapping-feature based speech recognition

A fuzzy acoustic-phonetic decoder for speech recognition

Syllable-level desynchronisation of phonetic features for speech recognition

A probabilistic framework for feature-based speech recognition

Modeling context-dependent phonetic units in a continuous speech recognition system for Mandarin Chinese

JANUS-II: towards spontaneous Spanish speech recognition

Reduced semi-continuous models for large vocabulary continuous speech recognition in Dutch

Validating different flexible vocabulary approaches on the Swiss French PolyPhone and PolyVar databases

Use of a reliability coefficient in noise cancelling by neural net and weighted matching algorithms

Likelihood normalization using an ergodic HMM for continuous speech recognition

Dynamic control of a production model [speech]

Speech recognition using sub-word units dependent on phonetic contexts of both training and recognition vocabularies

Hidden Markov models merging acoustic and articulatory information to automatic speech recognition

Creation of unseen triphones from diphones and monophones using a speech production approach

Speaker-independent dictation of Chinese speech with 32K vocabulary

Using accent-specific pronunciation modelling for robust speech recognition

Dictionary learning for spontaneous speech recognition

Comparison of channel normalisation techniques for automatic speech recognition over the phone

Anchor point detection for continuous speech recognition in Spanish: the spotting of phonetic events

Cepstral compensation by polynomial approximation for environment-independent speech recognition

Effect of speech coders on speech recognition performance

Wavelet transforms for non-uniform speech recognition systems

A binaural model as a front-end for isolated word recognition

A new speech enhancement: speech stream segregation

Head automata for speech translation

Word clustering with parallel spoken language corpora

Toward translating Korean speech into other languages

VERBMOBIL: the evolution of a complex large speech-to-speech translation system

Translation of conversational speech with JANUS-II

Non-segmental analysis and synthesis based on a speech database

Microsegment synthesis-economic principles in a low-cost solution

Whistler: a trainable text-to-speech system

Generation of multiple synthesis inventories by a bootstrapping procedure

Modeling segmental duration in German text-to-speech synthesis

Autolabelling Japanese ToBI

General phrase speaker verification using sub-word background models and likelihood-ratio scoring

Unknown-multiple signal source clustering problem using ergodic HMM and applied to speaker classification

GMM and ARVM cooperation and competition for text-independent speaker recognition on telephone speech

Selective use of the speech spectrum and a VQGMM method for speaker identification

Speaker verification through large vocabulary continuous speech recognition

Predictive neural networks in text independent speaker verification: an evaluation on the SIVA database

Durational characteristics of Hindi consonant clusters

The use of wavelet transforms in phoneme recognition

Acoustic properties of phonemes in continuous speech for different speaking rate

Prosodic parameterization of spoken Japanese based on a model of the generation process of F/sub 0/ contours

A logistic regression model for detecting prominences

High-quality prosodic modification of speech signals

On the syllable structures of Chinese relating to speech recognition

Can a moraic nasal occur word-initially in Japanese?

Perceptual assimilation of American English vowels by Japanese listeners

Context and speaker effects in the perceptual assimilation of German vowels by American listeners

Examination of a perceptual non-native speech contrast: pharyngealized/non-pharyngealized discrimination by French-speaking adults

Context-dependent relevance of burst and transitions for perceived place in stops: it's in production, not perception

Context-dependent Relevance Of Burst And Transitions For Perceived Place In Stops: It's In Production, Not Perception

The perception of morae in long vowels: comparison among Japanese, Korean and English speakers

Juncture cues to disfluency

Effects of duration and formant movement on vowel perception

Benchmarking human performance for continuous speech recognition

Intelligibility of speech with filtered time trajectories of spectral envelopes

Perceptual use of vowel and speaker information in breath sounds

The role of neighborhood relative frequency in spoken word recognition

Transitional probability and phoneme monitoring

Identification of vowel features from French stop bursts

Listening in a second language

Perception of lexical tone across languages: evidence for a linguistic mode of processing

Acoustic correlates to the effects of talker variability on the perception of English /r/ and /l/ by Japanese listeners

Natural communication with machines-progress and challenge

Volume 3 - 1996

Volume 2 - 1996

Volume 1 - 1996

Likelihood normalization using an ergodic HMM for continuous speech recognition

Content Provider	IEEE Xplore Digital Library
Author	Ozeki, K.
Copyright Year	1996
Description	Author affiliation: Univ. of Electro-Commun., Chofu, Japan (Ozeki, K.)
Abstract	In recent speech recognition technology, the score of a hypothesis is often defined on the basis of HMM likelihood. As is well known, however, direct use of the likelihood as a scoring function causes difficult problems, especially when the length of a speech segment varies depending on the hypothesis, as in word-spotting, and some kind of normalization is indispensable. In this paper, a new method of likelihood normalization using an ergodic HMM is presented, and its performance is compared with those of conventional ones. The comparison is made from three points of view: recognition rate, word-end detection power and mean hypothesis length. It is concluded that the proposed method gives the best overall performance.
Starting Page	2301
Ending Page	2304
File Size	389659
Page Count	4
File Format	PDF
ISBN	0780335554
DOI	10.1109/ICSLP.1996.607267
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	1996-10-03
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Vocabulary Viterbi algorithm Decision theory Hidden Markov models Speech recognition Probability Mutual information
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in