Phonotactic Models Research Articles

Is Sour Grapes Learnable? A Computational and Experimental Approach

In this paper, I present results from simulations using three different maximum entropy phonotactic models (Hayes & Wilson, 2008; Moreton et al., 2017): one that can only represent Sour Grapes, one that can only represent standard, attested harmony, and one that has the expressive power to capture both patterns. I then present results from an experiment designed to test the predictions of these models and find that humans behave most like the model that can capture both generalizations—challenging the idea that Sour Grapes is categorically unlearnable.

Discovering phonetic inventories with crosslingual automatic speech recognition

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well as zero-shot learning in order to build ASR systems for these low-resource languages. While it has been shown that the pooling of resources from multiple languages is helpful, we have not yet seen a successful application of an ASR model to a language unseen during training. A crucial step in the adaptation of ASR from seen to unseen languages is the creation of the phone inventory of the unseen language.The ultimate goal of our work is to build the phone inventory of a language unseen during training in an unsupervised way without any knowledge about the language. In this paper, we (1) investigate the influence of different factors (i.e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language; (2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation; and (3) present different methods to build a phone inventory of an unseen language in an unsupervised way. To that end, we conducted mono-, multi-, and crosslingual experiments on a set of 13 phonetically diverse languages and several in-depth analyses. We found a number of universal phone tokens (IPA symbols) that are well-recognized cross-linguistically. Through a detailed analysis of results, we conclude that unique sounds, similar sounds, and tone languages remain a major challenge for phonetic inventory discovery.

Learning Nonlocal Phonotactics in a Strictly Piecewise Probabilistic Phonotactic Model

Phonotactic learning is a crucial aspect of phonological acquisition and has figured significantly in computational research in phonology (Prince & Tesar 2004). However, one persistent challenge for this line of research is inducing non-local co-occurrence patterns (Hayes & Wilson 2008). The current study develops a probabilistic phonotactic model based on the Strictly Piecewise class of subregular languages (Heinz 2010). The model successfully learns both segmental and featural representations, and correctly predicts the acceptabilities of the nonce forms in Quechua (Gouskova & Gallagher 2020).

Incorporating tone in the modelling of wordlikeness judgements

Various phonotactic models have been proposed for the prediction of wordlikeness judgements, most of which have focused primarily on segments. This article aims to model wordlikeness judgements when tone is incorporated. We first show how the two major determinants of wordlikeness judgements, i.e. phonotactic probability and neighbourhood density, can be measured when tone is involved. To test the role of the two determinants of wordlikeness judgements in a tone language, judgement data were obtained from speakers of Cantonese. Bayesian modelling was then used to model the judgement data, showing that phonotactic probability, but not neighbourhood density, influences wordlikeness judgements. We also show that phonotactic probability affects the tendency to judge items as absolutely perfect or more or less wordlike, while it does not affect judgements that an item is absolutely not wordlike. Implications of these results for phonotactic modelling and processes involved in wordlikeness judgements are discussed.

Accidental Gaps and Surface-Based Phonotactic Learning: A Case Study of South Bolivian Quechua

The lexicon of a natural language does not contain all of the phonological structures that are grammatical. This presents a fundamental challenge to the learner, who must distinguish linguistically significant restrictions from accidental gaps ( Fischer-Jørgensen 1952 , Halle 1962 , Chomsky and Halle 1965 , Pierrehumbert 1994 , Frisch and Zawaydeh 2001 , Iverson and Salmons 2005 , Gorman 2013 , Hayes and White 2013 ). The severity of the challenge depends on the size of the lexicon ( Pierrehumbert 2001 ), the number of sounds and their frequency distribution ( Sigurd 1968 , Tambovtsev and Martindale 2007 ), and the complexity of the generalizations that learners must entertain ( Pierrehumbert 1994 , Hayes and Wilson 2008 , Kager and Pater 2012 , Jardine and Heinz 2016 ). In this squib, we consider the problem that accidental gaps pose for learning phonotactic grammars stated on a single, surface level of representation. While the monostratal approach to phonology has considerable theoretical and computational appeal ( Ellison 1993 , Bird and Ellison 1994 , Scobbie, Coleman, and Bird 1996 , Burzio 2002 ), little previous research has investigated how purely surface-based phonotactic grammars can be learned from natural lexicons (but cf. Hayes and Wilson 2008 , Hayes and White 2013 ). The empirical basis of our study is the sound pattern of South Bolivian Quechua, with particular focus on the allophonic distribution of high and mid vowels. We show that, in characterizing the vowel distribution, a surface-based analysis must resort to generalizations of greater complexity than are needed in traditional accounts that derive outputs from underlying forms. This exacerbates the learning problem, because complex constraints are more likely to be surface-true by chance (i.e., the structures they prohibit are more likely to be accidentally absent from the lexicon). A comprehensive quantitative analysis of the Quechua lexicon and phonotactic system establishes that many accidental gaps of the relevant complexity level do indeed exist. We propose that, to overcome this problem, surface-based phonotactic models should have two related properties: they should use distinctive features to state constraints at multiple levels of granularity, and they should select constraints of appropriate granularity by statistical comparison of observed and expected frequency distributions. The central idea is that actual gaps typically belong to statistically robust feature-based classes, whereas accidental gaps are more likely to be featurally isolated and to contain independently rare sounds. A maximum-entropy learning model that incorporates these two properties is shown to be effective at distinguishing systematic and accidental gaps in a whole-language phonotactic analysis of Quechua, outperforming minimally different models that lack features or perform nonstatistical induction.

Sonority Sequencing in Polish: the Combined Roles of Prior Bias & Experience

A growing body of behavioral results demonstrates cross-linguistic sensitivity to the SSP (Daland et al. 2011; Berent et al. 2007; Berent et al. 2008; Jarosz to appear; Ren, Gao & Morgan 2010). These consistent findings suggest a role for prior bias in phonological learning, but recent modeling studies question this conclusion, showing that for some languages these preferences can be derived from the input (Daland et al. 2011; Hayes 2011). Building on these results and Jarosz’s (to appear) developmental findings for Polish, the present paper investigates adult Polish speakers’ sensitivity to the SSP experimentally and computationally. We report the results of an online acceptability judgment experiment focusing on initial clusters and present the results of computational simulations evaluating the ability of phonotactic models to predict participants’ ratings on the basis of the lexical statistics of Polish. Our main findings are that 1) SSP is predictive of adults’ ratings, 2) sonority projection arises in both attested and unattested clusters, 3) while phonotactic models have significant predictive value, they do not subsume the SSP preferences observed in the participants’ ratings, and 4) participants’ sonority sequencing preferences are not entirely compatible with the SSP, suggesting a combined effect of prior bias and experience.

Input frequency and the acquisition of syllable structure in Polish

ABSTRACTThis article examines phonological development and its relationship to input statistics. Using novel data from a longitudinal corpus of spontaneous child speech in Polish, we evaluate and compare the predictions of a variety of input-based phonotactic models for syllable structure acquisition. We find that many commonly examined input statistics can make dramatically different predictions, as do different assumptions about the representational units over which statistics are calculated. We find that development is sensitive to multiple abstract units of phonological representation, supporting a crucial role for feature-based generalization. We also identify departures between the predictions of the best phonotactic models and children’s production patterns that indicate that input sensitivity alone cannot fully explain the developmental patterns. We discuss the role of universal markedness and phonetic difficulty and argue that a full explanation requires reference to these biases.

Phonotactic Model for Spoken Language Identification in Indian Language Perspective

Indian Languages are Indo-Aryan being influenced by Sanskrit or Dravidian being influenced by Tamil. Dravidian Languages have the influence of Sanskrit also. All Indian Languages have the influence of Pali language for which the graphemes are being influenced Brahmi. All the Indian languages are phonetic in nature. Every Indian language has its distinctive phone sets. North Indian languages are IndoAryan and South Indian Languages are Dravidian. Considering their respective Phonetic properties during speaking we have tried to consider the special CV behaviour of the language in their syllables and are able to identify the Language analysing it with the limited training data set available using the SVM Classifier. During this process we have analysed the PPR Language Modelling concept for four major Indian languages like Hindi, Bengali, Oriya, and Telugu and the results are quite appreciable. General Terms Spoken Language Identification, Speech Processing, Support Vector Machine

Text- and speech-based phonotactic models for spoken language identification of Basque and Spanish

This paper presents a series of spoken language identification experiments involving Spanish and Basque. Spanish and Basque are both official languages in the Basque Country, a region located in northern Spain. We focused our research on the study of several phonotactic-based methodologies, analysing at the same time the performance of phonotactic models trained from text and speech samples and the use of phone and phone sequences as decoding units. Although we focus mainly on Spanish–Basque identification, the analysis is later extended to English, so that more generic conclusions can be drawn. From the bilingual results, we can conclude that the text-based phonotactic models can perform similarly to the audio-based ones when applied to read speech. Moreover, when using task-specific information it is also possible to achieve a high accuracy. The use of phone sequences as decoding units results, in most of the cases, in a decrease in performance and appears to be useful when constraining the phone decoders to those sequences. Similar conclusions can be drawn from the trilingual experiments.

Enrollment and modeling method and apparatus for robust speaker dependent speech models

Speech recognition and the generation of speech recognition models is provided including the generation of unique phonotactic garbage models (15) to identify speech by, for example, English language constraints in addition to noise, silence and other non-speech models (11) and for speech recognition specific word models.

Spoken language recognition-a step toward multilinguality in speech processing

Automatic recognition of spoken languages has become an important feature in a variety of speech-enabled multilingual applications which, besides accuracy, also demand for efficient and linguistically scalable algorithms. This paper deals with a particularly successful approach based on phonotactic-acoustic features and presents systems for language identification as well as for unknown-language rejection. An architecture with multipath decoding, improved phonotactic models using binary-tree structures, and acoustic pronunciation models serve as a framework for experiments and discussion on these two tasks. In particular, language identification accuracy on a telephone-speech task (NIST'95 evaluation) in six and nine languages is presented together with results from a perceptual experiment carried out with human listeners. The performance of language rejection based on phonotactic modeling combined with a monolingual LVCSR system in the domain of broadcast news transcription is also reported. Besides yielding state-of-the-art performance, the described systems are computationally inexpensive and easily extensible (scalable) to new languages without the need for linguistic experts.

Development of an acoustic-phonetic hidden Markov model for continuous speech recognition

The techniques used to develop an acoustic-phonetic hidden Markov model, the problems associated with representing the whole acoustic-phonetic structure, the characteristics of the model, and how it performs as a phonetic decoder for recognition of fluent speech are discussed. The continuous variable duration model was trained using 450 sentences of fluent speech, each of which was spoken by a single speaker, and segmented and labeled using a fixed number of phonemes, each of which has a direct correspondence to the states of the matrix. The inherent variability of each phoneme is modeled as the observable random process of the Markov chain, while the phonotactic model of the unobservable phonetic sequence is represented by the state transition matrix of the hidden Markov model. The model assumes that the observed spectral data were generated by a Gaussian source. However, an analysis of the data shows that the spectra for the most of the phonemes are not normally distributed and that an alternative representation would be beneficial.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>