Development Of A Pos Tagger For Malayalam-An Experience

A Parts of Speech tagger for Malayalam which uses a stochastic approach has been proposed. The tagger makes use of word frequencies and bigram statistics from a corpus. The morphological analyzer is used to generate a tagged corpus due to the unavailability of an annotated corpus in Malayalam. Although the experiments have been performed on a very small corpus, the results have shown that the statistical approach works well with a highly agglutinative language like Malayalam

Extension schemes for the Alignment Model of English-Malayalam Statistical Machine Translator

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam sentence using statistical models. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set among the sentence pairs of the source and target language before subjecting them for training. This paper deals with certain techniques which can be adopted for improving the alignment model of SMT. Methods to incorporate the parts of speech information into the bilingual corpus has resulted in eliminating many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Presence of Malayalam words with predictable translations has also contributed in reducing the insignificant alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics.

A Hybrid Architecture for Recognising Speech Signals in Malayalam

Speech is the primary, most prominent and convenient means of communication in audible language. Through speech, people can express their thoughts, feelings or perceptions by the articulation of words. Human speech is a complex signal which is non stationary in nature. It consists of immensely rich information about the words spoken, accent, attitude of the speaker, expression, intention, sex, emotion as well as style. The main objective of Automatic Speech Recognition (ASR) is to identify whatever people speak by means of computer algorithms. This enables people to communicate with a computer in a natural spoken language. Automatic recognition of speech by machines has been one of the most exciting, significant and challenging areas of research in the field of signal processing over the past five to six decades. Despite the developments and intensive research done in this area, the performance of ASR is still lower than that of speech recognition by humans and is yet to achieve a completely reliable performance level. The main objective of this thesis is to develop an efficient speech recognition system for recognising speaker independent isolated words in Malayalam.

Intonation contours vs. syntactic structure as predictors of apparent segmentation

This paper is a review of a study on perception and comprehension of speech using syntactic, visual and acoustic information.

A technique to train auditory and visual memory for speech patterns in young hearing-impaired children

This paper details a technique for training auditory memory for length of speech sounds in preschool children with a profound hearing loss.

Perceptual aspects of a three-dimensional vowel space

This dissertation examines the auditory-perceptual theory of speech perception and the concept and validity of perceptual target zones for vowels.

Speech audiometry in English, Portuguese, and Spanish

This paper is a review of speech audiometry materials in the following languages: English, Portuguese and Spanish.

Usage of oral skills by orally educated deaf adults

This paper discusses oral deaf adults and use of speech.

Dichotic identification of complex sounds

This paper is a study of speech perception and related variables to better understand the psychoacoustics of speech.

Production of tense marking in successive bilingual children: when do they converge with their monolingual peers?

Children with English as a second language (L2) with exposure of 18 months or less exhibit similar difficulties to children with Specific Language Impairment in tense marking, a marker of language impairment for English. This paper examines whether L2 children with longer exposure converge with their monolingual peers in the production of tense marking. 38 Turkish-English L2 children with a mean age of 7;8 and 33 monolingual age-matched controls completed the screening test of the Test of Early Grammatical Impairment (TEGI). The L2 children as a group were as accurate as the controls in the production of -ed, but performed significantly lower than the controls in the production of third person –s. Age and YoE affected the children’s performance. The highest age-expected performance on the TEGI was attested in eight and nine year-old children who had 4-6 YoE. L1 and L2 children performed better in regular compared to irregular verbs, but L2 children overregularized more than L1 children and were less sensitive to the phonological properties of verbs. The results show that tense marking and the screening test of the TEGI may be promising for differential diagnosis in eight and nine year-old L2 children with at least four YoE.

Treatment of written verb and written sentence production in an individual with aphasia: A clinical study

Background: Although the efficacy of treatments for spoken verb and sentence production deficits in aphasia has been documented widely, less is known about interventions for written verb and written sentence production deficits. Aims: This study documents a treatment aiming to improve production of (a) written subject-verb sentences (involving intransitive verbs) and (b) written subject-verb-object sentences (involving transitive verbs). Methods & Procedures: The participant, a 63-year-old female aphasic speaker, had a marked language comprehension deficit, apraxia of speech, relatively good spelling abilities, and no hemiplegia. The treatment involved intransitive verbs producing subject-verb active sentences and transitive verbs producing subject-verb-object active non-reversible sentences. The treatment was undertaken in the context of current UK clinical practice. Outcomes & Results: Statistical improvements were noted for the trained sets of verbs and sentences. Other improvements were also noted in LW's ability to retrieve some non-treated verbs and construct written sentences. Treatment did not generalise to sentence comprehension and letter spelling to dictation. Conclusions: Our participant's ability to write verbs and sentences improved as a result of the treatment.

Frequency of word-use predicts rates of lexical evolution throughout Indo-European history

Greek speakers say "ovpa", Germans "schwanz'' and the French "queue'' to describe what English speakers call a 'tail', but all of these languages use a related form of 'two' to describe the number after one. Among more than 100 Indo-European languages and dialects, the words for some meanings (such as 'tail') evolve rapidly, being expressed across languages by dozens of unrelated words, while others evolve much more slowly-such as the number 'two', for which all Indo-European language speakers use the same related word-form(1). No general linguistic mechanism has been advanced to explain this striking variation in rates of lexical replacement among meanings. Here we use four large and divergent language corpora (English(2), Spanish(3), Russian(4) and Greek(5)) and a comparative database of 200 fundamental vocabulary meanings in 87 Indo-European languages(6) to show that the frequency with which these words are used in modern language predicts their rate of replacement over thousands of years of Indo-European language evolution. Across all 200 meanings, frequently used words evolve at slower rates and infrequently used words evolve more rapidly. This relationship holds separately and identically across parts of speech for each of the four language corpora, and accounts for approximately 50% of the variation in historical rates of lexical replacement. We propose that the frequency with which specific words are used in everyday language exerts a general and law-like influence on their rates of evolution. Our findings are consistent with social models of word change that emphasize the role of selection, and suggest that owing to the ways that humans use language, some words will evolve slowly and others rapidly across all languages.

The role of drama in the teaching of speaking and listening as the basis for social capital

This paper explores how the concept of 'social capital' relates to the teaching of speaking and listening. The argument draws on Bourdieu's notion that a common language is an illusion but posits that an understanding of the grammar of speech can be productive in the development of both an understanding of what constitutes effective speech and the development of competence in speaking. It is argued that applying structuralist notions of written grammar is an inadequate approach to understanding speech acts or enhancing the creative use of speech. An analysis is made of how typical features of speech relate to dramatic dialogue and how the meaning of what is said is contingent upon aural and visual signifiers. On this basis a competent speaker is seen as being one who produces expressions appropriate for a range of situations by intentionally employing such signifiers. The paper draws on research into the way drama teachers make explicit reference to and use of semiotics and dramatic effectiveness in order to improve students' performance and by so doing empower them to increase their social capital. Ultimately, it is concluded that helping students identify, analyse and employ the aural, visual and verbal grammar of spoken English is not an adjunct to the subject of drama, but an intrinsic part of understanding the art form. What is called for is a re-appraisal by drama teachers of their own understanding of concepts relating to speech acts in order to enhance this area of their work.

Steady-spectrum contexts and perceptual compensation for reverberation in speech identification

Perceptual compensation for reverberation was measured by embedding test words in contexts that were either spoken phrases or processed versions of this speech. The processing gave steady-spectrum contexts with no changes in the shape of the short-term spectral envelope over time, but with fluctuations in the temporal envelope. Test words were from a continuum between "sir" and "stir." When the amount of reverberation in test words was increased, to a level above the amount in the context, they sounded more like "sir." However, when the amount of reverberation in the context was also increased, to the level present in the test word, there was perceptual compensation in some conditions so that test words sounded more like "stir" again. Experiments here found compensation with speech contexts and with some steady-spectrum contexts, indicating that fluctuations in the context's temporal envelope can be sufficient for compensation. Other results suggest that the effectiveness of speech contexts is partly due to the narrow-band "frequency-channels" of the auditory periphery, where temporal-envelope fluctuations can be more pronounced than they are in the sound's broadband temporal envelope. Further results indicate that for compensation to influence speech, the context needs to be in a broad range of frequency channels. (c) 2007 Acoustical Society of America.

The aetiology and treatment of developmental stammering in childhood

Developmental stammering (DS, also known as idiopathic stammering or stuttering) is a disorder of speech fluency that affects approximately 0.75% to 1% of the populations of Great Britain, Australia and America,(1-4) although a recent study puts the point prevalence figure at between 1% and 3% in the UK.(5) Prevalence is generally thought to be similar amongst communities worldwide, although there have been occasional suggestions that this figure might be lower in countries where there is less pressure on verbal acuity.(6) DS may be distinguished from neurogenic stammering, which can occur subsequent to neurological damage of various aetiologies (for example, stroke, tumour, degenerative disease) and psychogenic stammering, whose onset can be related to a significant psychological event such as bereavement. While a diagnosis of neurogenic stammering might be made in early childhood and adolescence, both neurogenic and psychogenic types are typically associated with an adult onset. DS is by far the most common form of stammering and usually develops in the pre-school years. The mean age at onset is 4 2, with 75% of cases beginning before the age of 6.(1) However, occasionally, stammering onset may be seen as late as 12 or 13 years of age.