Turkish Broadcast News Transcription and Retrieval

Arisoy, Ebru; Can, Doğan; Parlak, Siddika; Sak, Haşim; Saraçlar, Murat

doi:10.1109/tasl.2008.2012313

Cited by 79 publications

(53 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, large vocabulary continuous speech recognition (LVCSR) systems have become available for Turkish broadcast news transcription [6]. An HTK based version of this system is also available [8].…”

Section: Properties Of the Considered Languagesmentioning

confidence: 99%

“…We integrated a Weighted Finite-State Transducer (WFST) based large-vocabulary continuous speech recognition system developed at Bogazici University into this multimodal communication platform [6,48]. The integrated system is currently capable of recognizing just Turkish utterances since language and acoustic models were readily available only for Turkish.…”

Section: Continuous Speech Recognitionmentioning

confidence: 99%

“…The acoustic model uses hidden Markov models (HMMs) trained on 188 hours of broadcast news speech data [6,8]. In the acoustic model, there are 10 843 triphone HMM states and 11 Gaussians per state with the exception of the 23 Gaussians for the silence HMM.…”

Section: Continuous Speech Recognitionmentioning

confidence: 99%

“…The text corpora that we used for estimating the parameters of statistical language models are composed of 182.3 million-words BOUN NewsCor corpus collected from news portals in Turkish [47] and 1.3 million-words text corpus (BN Corpus) obtained from the transcriptions of the Turkish Broadcast News speech database [6].…”

Section: Continuous Speech Recognitionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic fingersign-to-speech translation system

Hrúz

Campr

Dikici

et al. 2011

J Multimodal User Interfaces

View full text Add to dashboard Cite

The aim of this paper is to help the communication of two people, one hearing impaired and one visually impaired by converting speech to fingerspelling and fingerspelling to speech. Fingerspelling is a subset of sign language, and uses finger signs to spell letters of the spoken or written language. We aim to convert finger spelled words to speech and vice versa. Different spoken languages and sign languages such as English, Russian, Turkish and Czech are considered.

show abstract

Section: Properties Of the Considered Languagesmentioning

confidence: 99%

Section: Continuous Speech Recognitionmentioning

confidence: 99%

Section: Continuous Speech Recognitionmentioning

confidence: 99%

Section: Continuous Speech Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic fingersign-to-speech translation system

Hrúz

Campr

Dikici

et al. 2011

J Multimodal User Interfaces

View full text Add to dashboard Cite

show abstract

“…Due to this agglutinative nature, the word-based automatic speech recognition (ASR) system with a moderate size vocabulary suffers from the problem of a high out-ofvocabulary (OOV) rate. To increase the vocabulary's coverage, sub-words are utilized as the recognition units in the automatic transcription task for agglutinative languages such as Estonian [1], Hungarian [2], Finnish [3], and Turkish [4]. Morphemes, which are obtained from the morphological parsing, and statistical sub-words, which are derived from the data-driven splitting, are two commonly used sub-lexical units.…”

Section: Introductionmentioning

confidence: 99%

Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages

Pan

Zhao

et al. 2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYMorphemes, which are obtained from morphological parsing, and statistical sub-words, which are derived from data-driven splitting, are commonly used as the recognition units for speech recognition of agglutinative languages. In this letter, we propose a discriminative approach to select the splitting result, which is more likely to improve the recognizer's performance, for each distinct word type. An objective function which involves the unigram language model (LM) probability and the count of misrecognized phones on the acoustic training data is defined and minimized. After determining the splitting result for each word in the text corpus, we select the frequent units to build a hybrid vocabulary including morphemes and statistical sub-words. Compared to a statistical sub-word based system, the hybrid system achieves 0.8% letter error rates (LERs) reduction on the test set.

show abstract

Speech Retrieval

Chelba¹,

Hazen²,

Ramabhadran³

et al. 2011

Spoken Language Understanding

View full text Add to dashboard Cite

In this chapter we discuss the retrieval and browsing of spoken audio documents. We focus primarily on the application of document search where a user provides a query and the system returns a set of audio documents that best match the query. The primary technical challenges of speech retrieval lie in the retrieval system's ability to deal with imperfect speech recognition technology that produces errorful output due to misrecognitions cause by inadequate statistical models or out-of-vocabulary words. This chapter provides an overview of the common tasks and data sets, evaluation metrics, and algorithms most commonly used in this growing area of research.

show abstract

Turkish Broadcast News Transcription and Retrieval

Cited by 79 publications

References 34 publications

Automatic fingersign-to-speech translation system

Automatic fingersign-to-speech translation system

Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages

Speech Retrieval

Contact Info

Product

Resources

About