Building a speech repository for a Serbian LVCSR system

Suzic, Sinisa; Ostrogonac, Stevan; Pakoci, Edvin; Bojanić, Milana

doi:10.5937/telfor1402109s

Cited by 6 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first part contains audio book recordings, recorded in studio environment by professional speakers. A large part of this database was already mentioned in previous papers [14], but lately it has been expanded by several new audio books. This database part is responsible for 168 hours of data in total, out of which about 140 hours is pure speech (the rest is silence).…”

Section: Methodsmentioning

confidence: 99%

Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition

Pakoci

Popović

Pekar

2019

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Serbian is in a group of highly inflective and morphologically rich languages that use a lot of different word suffixes to express different grammatical, syntactic, or semantic features. This kind of behaviour usually produces a lot of recognition errors, especially in large vocabulary systems—even when, due to good acoustical matching, the correct lemma is predicted by the automatic speech recognition system, often a wrong word ending occurs, which is nevertheless counted as an error. This effect is larger for contexts not present in the language model training corpus. In this manuscript, an approach which takes into account different morphological categories of words for language modeling is examined, and the benefits in terms of word error rates and perplexities are presented. These categories include word type, word case, grammatical number, and gender, and they were all assigned to words in the system vocabulary, where applicable. These additional word features helped to produce significant improvements in relation to the baseline system, both for n-gram-based and neural network-based language models. The proposed system can help overcome a lot of tedious errors in a large vocabulary system, for example, for dictation, both for Serbian and for other languages with similar characteristics.

show abstract

Section: Methodsmentioning

confidence: 99%

Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition

Pakoci

Popović

Pekar

2019

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…This needs to be kept in mind when analysing WER results for different functional styles. All audio recordings were sampled at 16 kHz, 16 bits per sample, mono PCM [26].…”

Section: Word Error Rate Evaluationmentioning

confidence: 99%

Morphology-based vs Unsupervised Word Clustering for Training Language Models for Serbian

2019

APH

View full text Add to dashboard Cite

When training language models (especially for highly inflective languages), some applications require word clustering in order to mitigate the problem of insufficient training data or storage space. The goal of word clustering is to group words that can be well represented by a single class in the sense of probabilities of appearances in different contexts. This paper presents comparative results obtained by using different approaches to word clustering when training class N-gram models for Serbian, as well as models based on recurrent neural networks. One approach is unsupervised word clustering based on optimized Brown's algorithm, which relies on bigram statistics. The other approach is based on morphology, and it requires expert knowledge and language resources. Four different types of textual corpora were used in experiments, describing different functional styles. The language models were evaluated by both perplexity and word error rate. The results show notable advantage of introducing expert knowledge into word clustering process.

show abstract

“…regarding the Torlak dialect (Vuković, 2021), resources for automatic speech recognition and synthesis (Delić et al, 2013;Suzić et al, 2014), and specialised spoken corpora, such as the SCECL 1 corpus on early child language (Anđelković et al, 2001) and SrMaCo 2 corpus on language of Serbian minority in Hungary.…”

Section: Introductionmentioning

confidence: 99%

Converting raw transcripts into an annotated and turn-aligned TEI-XML corpus: the example of the Corpus of Serbian Forms of Address

Lemmenmeier-Batinić

2021

SLO2.0

View full text Add to dashboard Cite

This paper describes the procedure of building a TEI-XML corpus of spoken Serbian starting from raw transcripts. The corpus consists of semi–structured interviews, which were gathered with the aim of investigating forms of address in Serbian. The interviews were thoroughly transcribed according to GAT transcribing conventions. However, the transcription was carried out without tools that would control the validity of the GAT syntax, or align the transcript with the audio records. In order to offer this resource to a broader audience, we resolved the inconsistencies in the original transcripts, normalised the semi-orthographic transcriptions and converted the corpus into a TEI-format for transcriptions of speech. Further, we enriched the corpus by tagging and lemmatising the data. Lastly, we aligned the corpus turns to the corresponding audio segments by using a force-alignment tool. In addition to presenting the main steps involved in converting the corpus to the XML-format, this paper also discusses current challenges in the processing of spoken data, and the implications of data re-use regarding transcriptions of speech. This corpus can be used for studying Serbian from the perspective of interactional linguistics, for investigating morphosyntax, grammar, lexicon and phonetics of spoken Serbian, for studying disfluencies, as well as for testing models for automatic speech recognition and forced alignment. The corpus is freely available for research purposes.

show abstract

Building a speech repository for a Serbian LVCSR system

Cited by 6 publications

References 2 publications

Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition

Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition

Morphology-based vs Unsupervised Word Clustering for Training Language Models for Serbian

Converting raw transcripts into an annotated and turn-aligned TEI-XML corpus: the example of the Corpus of Serbian Forms of Address

Contact Info

Product

Resources

About