Abstract not found

Conversational speech exhibits considerable pronunciation variability, which has been shown to have a detrimental effect on the accuracy of automatic speech recognition. There have been many attempts to model pronunciation variation, including the use of decision-trees to generate alternate word pronunciations from phonemic baseforms. Use of such pronunciation models during recognition is known to improve accuracy. This paper describes the use of such pronunciation models during acoustic model training. Subtle difficulties in the straightforward use of alternatives to canonical pronunciations are first illustrated: it is shown that simply improving the accuracy of the phonetic transcription used for acoustic model training is of little benefit. Analysis of this paradox leads to a new method of accommodating nonstandard pronunciations: rather than allowing a phoneme in the canonical pronunciation to be realized as one of a few distinct alternate phones predicted by the pronunciation model, the HMM states of the phoneme's model are instead allowed to share Gaussian mixture components with the HMM states of the model of the alternate realization. Qualitatively, this amounts to making a soft decision about which surface-form is realized. Quantitative experiments on the Switchboard corpus show that this method improves accuracy by 1.7% (absolute).

This paper describes connectionist techniques for recognition of Broadcast News. The fundamental difference between connectionist systems and more conventional mixture-of-Gaussian systems is that connectionist models directly estimate posterior probabilities as opposed to likelihoods. Access to posterior probabilities has enabled us to develop a number of novel approaches to confidence estimation, pronunciation modelling and search. In addition we have investigated a new feature extraction technique based on the modulation-filtered spectrogram (MSG), and methods for combining multiple information sources. We have incorporated all of these techniques into a system for the transcription

Most large vocabulary continuous speech recognition (LVCSR) systems in the past decade have used a context-dependent phone as the fundamental acoustic unit. In this paper, we present one of the first robust LVCSR systems that uses a syllable-level acoustic unit for LVCSR on telephone-bandwidth speech. This effort is motivated by the inherent limitations in phone-based approaches — namely the lack of an easy and efficient way for modeling long-term temporal dependencies. A syllable unit spans a longer time frame, typically three phones, thereby offering a more parsimonious framework for modeling pronunciation variation in spontaneous speech. We present encouraging results which show that a syllable-based system exceeds the performance of a comparable triphone system both in terms of word error rate (WER) and complexity. The WER of the best syllable system reported here is 49.1 % on a standard SWITCHBOARD evaluation, a small improvement over the triphone system. We also report results on a much smaller recognition task, OGI Alphadigits, which was used to validate some of the benefits syllables offer over triphones. The syllable-based system exceeds the performance of the triphone system by nearly 20%, an impressive accomplishment since the alphadigits application consists mostly of phone-level minimal pair distinctions.

In order to help understand why gains in pronunciation modeling have proven so elusive, we investigated which kinds of pronunciation variation are well captured by triphone models, and which are not. We do this by examining the change in behavior of a recognizer as it receives further triphone training. We show that many of the kinds of variation which previous pronunciation models attempt to capture, including phone substitution or phone reduction, are in fact already well captured by triphones. Our analysis suggests new areas where future pronunciation models should focus, including syllable deletion. 1. INTRODUCTION Many studies of human-to-human speech have shown that pronunciation variation is a key factor contributing to the high error rates of current recognizers. For example [1] showed that Switchboard word error decreased from 40% to 8% if the dictionary pronunciation matched the actual pronunciation. While the need for better pronunciation modeling is widely acknowledged, ...

In developing telephone-based conversational systems, we foresee future systems capable of supporting multiple domains and flexible vocabulary. Users can pursue several topics of interest within a single telephone call, and the system is able to switch transparently among domains within a single dialog. This system is able to detect the presence of any out-of-vocabulary (OOV) words, and automatically hypothesizes each of their pronunciation, spelling and meaning. These can be confirmed with the user and the new words are subsequently incorporated into the recognizer lexicon for future use. This thesis

There are various kinds of adaptation which can be used to enhance the performance of automatic speech recognizers. This paper is about pronunciation adaptation at the lexical level, i.e. about modeling pronunciation variation at the lexical level. In the early years of automatic speech recognition (ASR) research, the amount of pronunciation variation was limited by using isolated words. Since the focus gradually shifted from isolated words to conversational speech, the amount of pronunciation variation present in the speech signals has increased, as has the need to model it. This is reflected by the growing attention for this topic. In this paper, an overview of the studies on lexicon adaptation is presented. Furthermore, many examples are mentioned of situations in which lexicon adaptation is likely to improve the performance of speech recognizers. Finally, it is argued that some assumptions made in current standard ASR systems are not in line with the properties of the speech signals. Consequently, the problem of pronunciation variation at the lexical level probably cannot be solved by simply adding new transcriptions to the lexicon, as it is generally done at the moment.

Current-generation automatic speech recognition #ASR# systems assume that words are readily decomposable into constituent phonetic components ##phonemes"#. A detailed linguistic dissection of state-of-the-art speech recognition systems indicates that the conventional phonemic #beads-on-a-string" approach is of limited utility, particularly with respect to informal, conversational material. The study shows that there is a signi#cantgapbetween the observed data and the pronunciation models of current ASR systems. It also shows that many important factors a#ecting recognition performance are not modeled explicitly in these systems.

In most speech recognition systems today, acoustic modeling and lexical modeling are viewed as separable problems. Currently the most popular approach is to manually define canonical word pronunciations in terms of phonetic units and let the acoustic models capture differences between actual spoken and canonical pronunciations implicitly with Gaussian mixture models. As a result, these models can be very broad, particularly for casual spontaneous speech. An alternative approach, explored in this thesis, is to learn a unit inventory and pronunciation dictionary from training data using a maximum likelihood objective function. In particular,

This paper focuses on modeling pronunciation variation in two different ways: data-derived and knowledge-based. The knowledge-based approach consists of using phonological rules to generate variants. The data-derived approach consists of performing phone recognition, followed by various pruning and smoothing methods to alleviate some of the errors in the phone recognition. Using phonological rules led to a small improvement in WER; whereas, using a data-derived approach in which the phone recognition was smoothed using simple decision trees (d-trees) prior to lexicon generation led to a significant improvement compared to the baseline. Furthermore, we found that 10% of variants generated by the phonological rules were also found using phone recognition, and this increased to 23% when the phone recognition output was smoothed by using d-trees. In addition, we propose a metric to measure confusability in the lexicon and we found that employing this confusion metric to prune variants resu...