Transitional Speech Units and Their Representation by Regressive Markov States: Applications to Spee - Speech and Audio Processing, IEEE Transactions on
نویسندگان
چکیده
Transitional speech units for American English are proposed and constructed via assimilation of active articulatory features. The effectiveness of a feature-based system exploiting the transitional speech units is demonstrated in evaluation experiments, where the new system with use of quadratic regressive states is shown to achieve error rate reduction of 21% compared with the system using only static subphonemic units.
منابع مشابه
Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states
AbsfractWe propose, implement, and evaluate a class of nonstationary-state hidden Markov models (HMM’s) having each state associated with a distinct polynomial regression function of time plus white Gaussian noise. The model represents the transitional acoustic trajectories of speech in a parametric manner, and includes the standard stationary-state HMM as a special, degenerated case. We develo...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملCepstrum-Based Deconvolution for Speech Dereverberation - Speech and Audio Processing, IEEE Transactions on
OBSERVATION PROBABILITY AND STATE DURATION-DEPENDENT OBSERVATION PROBABILITY (NO. OF TEST WORDS WAS 2810) I I I hameter I P ~ D D D S ~ ~ I NUMBERS OF MIXTURES BETWEEN STATE DURATION-INDEPENDENT Acoust, Speech, Signal Processing, vol. ASSP-33, pp 587-594, June 1985. [7] Y. J. Chung and C. K. Un, “Use of different numbers of mixtures in continuous density hidden Markov models,” IEE Electron. Let...
متن کاملLinear Prediction of the One-Sided Autocorrelation Sequence for Noisy Speech Recognition [Correspond - Speech and Audio Processing, IEEE Transactions on
The aim of this correspondence is to present a robust representation of speech based on AR modeling of the causal part of the autocorrelation sequence. In noisy speech recognition, this new representation achieves better results than several other related techniques.
متن کاملOnline hierarchical transformation of hidden Markov models for speech recognition
This paper proposes a novel framework of online hierarchical transformation of hidden Markov model (HMM) parameters for adaptive speech recognition. Our goal is to incrementally transform (or adapt) all the HMM parameters to a new acoustical environment even though most of HMM units are unseen in observed adaptation data. We establish a hierarchical tree of HMM units and apply the tree to dynam...
متن کامل