Articles

Benchmarking the performance for telephone-network-based speech recognition systems is hampered by two factors: lack of standardized databases for telephone network speech, and insuffi- cient understanding of the impact of the telephone network on rec- ognition systems. The N-TIMIT database was used in the experiments described in this paper in order …...

In this paper, baseline speech recognition performance is determined both for a single remote microphone and for a signal derived from a delay-and-sum beamformer using an eight-microphone linear array. An HMM-based, connected-speech, 38-word vocabulary (alphabet, digits, 'space', 'period'), talker-independent speech recognition system is used for testing performance. Normal performance, with …...

Speech recognition systems tend to be sensitive to unimportant steady-state variation in speech spectra (i.e. those caused by vary- ing the microphone or channel characteristics). There have been many attempts to solve this problem; however, these techniques are often computationally burdensome, especially for real-time implementation. Recently, Hermansy et el. [1] …...

This paper compares several different approaches to robust speech recognition. We review CMU's ongoing research in the use of acoustical pre-proeessing to achieve robust speech recog- nition, and we present the results of the first evaluation of pre- processing in the context of the DARPA standard ATIS domain for spoken …...

The time required for our translation system to handle a sentence of length I is a rapidly growing function of i. We describe here a method for analyzing a sentence into a series of pieces that can be translated sequentially. We show that for sentences with ten or fewer words, …...

This paper discusses complex structural changes dur- ing transfer within a non-destructive transfer framework. Though the description of each individual structural change is not difficult, special provision must be made when they are combined, because interaction between them sometimes causes unexpected problems. Transfer of coordinate struc- tures is also discussed …...

Machine-readable dictionaries provide the raw material from which to construct computationaily useful representations of the generic vocabulary contained within it. Many sublan- guages, however, are poorly represented in on-line dictionar- ies, ff represented at all. Vocabularies geared to specialized domains are necessary for many applications, such as text categorization and …...

The resolution of lexical ambiguity is important for most nat- ural language processing tasks, and a range of computational techniques have been proposed for its solution. None of these has yet proven effective on a large scale. In this paper, we de- scribe a method for lexical disambiguation of text …...

We have been addressing the problem of providing access to the free text in biomedical databases. The focus of our work is the development of SPECIALIST, an experimental NLP system for the biomedical domain. The system includes a broad coverage parser supported by a large lexicon, a module that provides …...

The effect of selecting varying numbers and kinds of fea- tures for use in predicting category membership was inves- tigated on the Reuters and MUC-3 text categorization data sets. Good categorization performance was achieved using a statistical classifier and a proportional assignment strat- egy. The optimal feature set size for …...

Traditional statistical speech recognition systems typically make strong assumptions about the independence of obser- vation frames and generally do not make use of segmental information. In contrast, when the segmentation is known, existing classifiers can readily accommodate segmental infor- mation in the decision process. We describe an approach to connected …...

For speaker-independent speech recognition, speaker variation is one of the major error sources. In this paper, a speaker-independentnor- malization network is constructed such that speaker variation effects can be minimized. To achieve this goal, multiple speaker clusters are constructed from the speaker-independent training database. A codeword-dependent neural network is associated …...

In an effort to advance the state of the art in continuous speech recognition employing hidden Markov models (HMM), Segmental Neural Nets (SNN) were introduced recently to ameliorate the well- known limitations of HMMs, namely, the conditional-independence limitation and the relative difficulty with which HMMs can handle segmental features. We …...

We discuss maximum a posteriori estimation of continuous density hid- den Markov models (CDHMM). The classical MLE reestimation algorithms, namely the forward-backward algorithm and the segmental k-means algo- rithm, are expanded and reestimation formulas are given for HMM with Gaussian mixture observation densities. Because of its adaptive nature, Bayesian learning …...

How to capture important acoustic clues and estimate essen- tial parameters reliably is one of the central issues in speech recognition, since we will never have sufficient training data to model various acoustic-phonetic phenomena. Success- ful examples include subword models with many smoothing techniques. In comparison with subword models, subphonetic …...

This paper introduces three recent topics in speech recognition research at NTT (Nippon Telegraph and Telephone) Human In- terface Laboratories. The first topic is a new HMM (hidden Markov model) technique that uses VQ-code bigrams to constrain the output probability distribution of the model according to the VQ-codes of previons …...

In this paper, we present evidence that the acquisition of the phrase structure of a natural language is possible without su- pervision and with a very small initial grammar. We describe a language learner that extracts distributional information from a corpus annotated with parts of speech and is able to …...

A new language model incorporating both N-gram and context-free ideas is proposed. This constrained context-free model is specified by a stochastic context-free prior distribu- tion with N-gram frequency constraints. The resulting dis- tribution is a Markov random field. Algorithms for sampling from this distribution and estimating the parameters of the …...

In this paper, we are looking into the adaptation issues of vocabulary-independent (VI) systems. Just as with speaker- adaptation in speaker-independent system, two vocabulary adaptation algorithms [5] are implemented in order to tailor the VI subword models to the target vocabulary. The first algorithm is to generate vocabulary-adapted clustering de- …...

We describe a generative probabilistic model of natural lan- guage, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorpo- rates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way. We use a corpus of …...