Lexicon-building methods for an acoustic sub-word based speech recognizer
03 Apr 1990-Vol. 1990, pp 729-732
TL;DR: The use of an acoustic subword unit (ASWU)-based speech recognition system for the recognition of isolated words is discussed and it is shown that the use of a modified k-means algorithm on the likelihoods derived through the Viterbi algorithm provides the best deterministic-type of word lexicon.
Abstract: The use of an acoustic subword unit (ASWU)-based speech recognition system for the recognition of isolated words is discussed. Some methods are proposed for generating the deterministic and the statistical types of word lexicon. It is shown that the use of a modified k-means algorithm on the likelihoods derived through the Viterbi algorithm provides the best deterministic-type of word lexicon. However, the ASWU-based speech recognizer leads to better performance with the statistical type of word lexicon than with the deterministic type. Improving the design of the word lexicon makes it possible to narrow the gap in the recognition performances of the whole word unit (WWU)-based and the ASWU-based speech recognizers considerably. Further improvements are expected by designing the word lexicon better. >
Citations
More filters
01 Jan 1999
TL;DR: This article exposes and develops the concept of ALISP (Automatic Language Independent Speech Processing), namely a general methodology which consists in inferring the intermediate representation between the acoustic and the linguistic levels, from speech and linguistic data rather than from a priori knowledge, with as little supervision as possible.
Abstract: The models used in current automatic speech recognition (or synthesis) systems are generally relying on a representation based on phonetic symbols. The phonetic transcription of a word can be seen as an intermediate representation between the acoustic and the linguistic levels, but the a priori choice of phonemes (or phone-like units) can be questioned, as probably non-optimal. Moreover, the phonetic representation has the drawback of being strongly language-dependent, which partly prevents reusability of acoustic resources across languages. In this article, we expose and develop the concept of ALISP (Automatic Language Independent Speech Processing), namely a general methodology which consists in inferring the intermediate representation between the acoustic and the linguistic levels, from speech and linguistic data rather than from a priori knowledge, with as little supervision as possible. We expose the benefits that can be expected from developing the ALISP approach, together with the key issues to be solved. We also present preliminary experiments that can be viewed as first steps towards the ALISP goal.
39 citations
Book•
08 May 2011
TL;DR: This work presents a fully statistical approach to model non--native speakers' pronunciation, based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary.
Abstract: In this work, the authors present a fully statistical approach to model non--native speakers' pronunciation. Second-language speakers pronounce words in multiple different ways compared to the native speakers. Those deviations, may it be phoneme substitutions, deletions or insertions, can be modelled automatically with the new method presented here.The methods is based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary. The implementation and functionality of the methodology has been proven and verified with a test set of non-native English in the regarding accent.The book is written for researchers with a professional interest in phonetics and automatic speech and speaker recognition.
37 citations
01 Jan 2005
TL;DR: Of the Dissertation Learning Features and Segments from Waveforms: A Statistical Model of Early Phonological Acquisition and its Applications.
Abstract: of the Dissertation Learning Features and Segments from Waveforms: A Statistical Model of Early Phonological Acquisition
34 citations
Cites result from "Lexicon-building methods for an aco..."
...This step is similar to the lexicon building task in ASWU systems (Paliwal, 1990) in that the mixture of lexical exemplars can be seen as a way of doing pronunciation modeling (Bacchiani, 1999)....
[...]
Dissertation•
01 Jan 2007
TL;DR: It is shown how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream, and two methods for automatically identifying sound clusters generated through pattern discovery are proposed and evaluated.
Abstract: We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to classify speech into categories defined by a pre-specified inventory of lexical units (i.e. phones or words). Instead, we attempt to discover such an inventory in an unsupervised manner by exploiting the structure of repeating patterns within the speech signal. We show how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream.
Our approach to unsupervised word acquisition utilizes a segmental variant of a widely used dynamic programming technique, which allows us to find matching acoustic patterns between spoken utterances. By aggregating information about these matching patterns across audio streams, we demonstrate how to group similar acoustic sequences together to form clusters corresponding to lexical entities such as words and short multi-word phrases. On a corpus of academic lecture material, we demonstrate that clusters found using this technique exhibit high purity and that many of the corresponding lexical identities are relevant to the underlying audio stream.
We demonstrate two applications of our pattern discovery procedure. First, we propose and evaluate two methods for automatically identifying sound clusters generated through pattern discovery. Our results show that high identification accuracy can be achieved for single word clusters using a constrained isolated word recognizer. Second, we apply acoustic pattern matching to the problem of speaker segmentation by attempting to find word-level speech patterns that are repeated by the same speaker. When used to segment a ten hour corpus of multi-speaker lectures, we found that our approach is able to generate segmentations that correlate well to independently generated human segmentations. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)
20 citations
Cites background from "Lexicon-building methods for an aco..."
...Researchers in the speech recognition community have devoted considerable effort to this task, which is primarily motivated by the goal of determining units for automatic speech recognition [40, 6, 53, 106, 62, 114, 113, 82]....
[...]
07 May 1996
TL;DR: An iterative unit design procedure is formulated which consistently uses a maximum likelihood (ML) objective in successive application of resegmentation and model re-estimation.
Abstract: The design of a speech recognition system based on acoustically-derived, segmental units can be divided in three steps: unit design, lexicon building and pronunciation modeling. We formulate an iterative unit design procedure which consistently uses a maximum likelihood (ML) objective in successive application of resegmentation and model re-estimation. The lexicon building allows multi-word entries in the lexicon but restricts the number of these entries in order to avoid a too costly search. Selected multi-word lexical entries are those with high frequency (such as function words) and those which consistently exhibit cross-word phone assimilation. The stochastic pronunciation model represents the likelihood of a particular acoustic segment sequence given the phonetic baseform of a lexical item, where the sequence of baseform phones are treated as a Markov state sequence and each state can emit multiple segments.
20 citations
Cites methods from "Lexicon-building methods for an aco..."
...Our approach is to combine two advances proposed in previous work: the use of acoustically-derived subword units [1] and segmental modeling [2, 3]....
[...]
...Taking an approach similar to that in [1], the maximum likelihood (ML) segmentation of the training data is found by use of dynamic programming (DP)....
[...]
...The di erence between the work described in [1] and the work described here is that we use a multivariate Gaussian model to compute segment likelihoods instead of using a Euclidean distance measure....
[...]
References
More filters
01 Feb 1989
TL;DR: In this paper, the authors provide an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and give practical details on methods of implementation of the theory along with a description of selected applications of HMMs to distinct problems in speech recognition.
Abstract: This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and gives practical details on methods of implementation of the theory along with a description of selected applications of the theory to distinct problems in speech recognition. Results from a number of original sources are combined to provide a single source of acquiring the background required to pursue further this area of research. The author first reviews the theory of discrete Markov chains and shows how the concept of hidden states, where the observation is a probabilistic function of the state, can be used effectively. The theory is illustrated with two simple examples, namely coin-tossing, and the classic balls-in-urns system. Three fundamental problems of HMMs are noted and several practical techniques for solving these problems are given. The various types of HMMs that have been studied, including ergodic as well as left-right models, are described. >
21,819 citations
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.
Abstract: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data. The basic properties of the algorithm are discussed and demonstrated by examples. Quite general distortion measures and long blocklengths are allowed, as exemplified by the design of parameter vector quantizers of ten-dimensional vectors arising in Linear Predictive Coded (LPC) speech compression with a complicated distortion measure arising in LPC analysis that does not depend only on the error vector.
7,935 citations
IBM1
TL;DR: This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
Abstract: Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of statistical models for use in speech recognition. We give special attention to determining the parameters for such models from sparse data. We also describe two decoding methods, one appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks. To illustrate the usefulness of the methods described, we review a number of decoding results that have been obtained with them.
1,637 citations
IBM1
TL;DR: An automatic technique for constructing Markov word models is described and results are included of experiments with speaker-dependent and speaker-independent models on several isolated-word recognition tasks.
Abstract: The Speech Recognition Group at IBM Research has developed a real-time, isolated-word speech recognizer called Tangora, which accepts natural English sentences drawn from a vocabulary of 20000 words. Despite its large vocabulary, the Tangora recognizer requires only about 20 minutes of speech from each new user for training purposes. The accuracy of the system and its ease of training are largely attributable to the use of hidden Markov models in its acoustic match component. An automatic technique for constructing Markov word models is described and results are included of experiments with speaker-dependent and speaker-independent models on several isolated-word recognition tasks. >
245 citations
TL;DR: A clustering algorithm based on a standard K-means approach which requires no user parameter specification is presented and experimental data show that this new algorithm performs as well or better than the previously used clustering techniques when tested as part of a speaker-independent isolated word recognition system.
Abstract: Studies of isolated word recognition systems have shown that a set of carefully chosen templates can be used to bring the performance of speaker-independent systems up to that of systems trained to the individual speaker. The earliest work in this area used a sophisticated set of pattern recognition algorithms in a human-interactive mode to create the set of templates (multiple patterns) for each word in the vocabulary. Not only was this procedure time consuming but it was impossible to reproduce exactly because it was highly dependent on decisions made by the experimenter. Subsequent work led to an automatic clustering procedure which, given only a set of clustering parameters, clustered patterns with the same performance as the previously developed supervised algorithms. The one drawback of the automatic procedure was that the specification of the input parameter set was found to be somewhat dependent on the vocabulary type and size of population to be clustered. Since a naive user of such a statistical clustering algorithm could not be expected, in general, to know how to choose the word clustering parameters, even this automatic clustering algorithm was not appropriate for a completely general word recognition system. It is the purpose of this paper to present a clustering algorithm based on a standard K-means approach which requires no user parameter specification. Experimental data show that this new algorithm performs as well or better than the previously used clustering techniques when tested as part of a speaker-independent isolated word recognition system.
218 citations