Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio

Nouza, Jan; Blavka, Karel; Bohac, Marek; Červa, Petr; Žďánský, Jindřich; Silovský, Jan; Prażak, Jan

doi:10.1007/978-3-642-27978-2_3

Cited by 14 publications

(17 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tools we consider include a context-sensitive spell checker, a grammar checker, and a stochastic model of error corrections. The tools are also tested on a corpus of transcribed speech [9]. Other plans include the use of syntactic annotation (functions and structure), and modifications and development of error taxonomy in response to users' feedback and the experience from annotating larger volumes of data.…”

Section: Resultsmentioning

confidence: 99%

Combining Manual and Automatic Annotation of a Learner Corpus

Jelínek

Štindlová

Rosen

et al. 2012

Text, Speech and Dialogue

View full text Add to dashboard Cite

Abstract. We present an approach to building a learner corpus of Czech, manually corrected and annotated with error tags using a complex grammar-based taxonomy of errors in spelling, morphology, morphosyntax, lexicon and style. This grammar-based annotation is supplemented by a formal classification of errors based on surface alternations. To supply additional information about non-standard or ill-formed expressions, we aim at a synergy of manual and automatic annotation, deriving information from the original input and from the manual annotation.

show abstract

Section: Resultsmentioning

confidence: 99%

Combining Manual and Automatic Annotation of a Learner Corpus

Jelínek

Štindlová

Rosen

et al. 2012

Text, Speech and Dialogue

View full text Add to dashboard Cite

show abstract

“…In the Czech Radio archive [1], several thousands of audio documents come from regional studios. For many years, each studio editor has had his/her own standard for data storing.…”

Section: Czech Radio Recordingsmentioning

confidence: 99%

“…It has been employed for broadcast news (BN) transcription in Czech since 2005 [8], and later also for several other Slavic languages. Recently, it has been intensively used in the project aimed at the transcription of the Czech radio archive [1].…”

Section: J Employed Asr Systemmentioning

confidence: 99%

“…We have faced this problem in projects whose goal is to automatically transcribe and index large audio archives. The largest one belongs to the Czech Radio company [1] and contains more than 100.000 spoken documents covering 90 years of broadcasting. Most recordings were digitized during the last decade and the MP3 format (with various settings) was used as the major standard.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech

Nouza

Červa

Silovský

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

This paper deals with the recognition of speech whose spectrum is notably distorted by lossy compression (namely MP3) or by some implementations of 'speech enhancement' techniques. We show that these non-linear treatments can introduce gaps in spectrum that significantly change the distribution of MFCCs and degrade performance of ASR. We propose a method that measures the level of spectrum distortion and use it for adding a controlled amount of noise to the signal. It effectively masks the gaps and helps namely in situations where the source and parameters of the distortion are not known and hence we cannot use a properly matched acoustic model. In spite of its simplicity, the method can improve significantly speech recognition of highly compressed or spectrally distorted signals. We demonstrate it in several large experiments conducted on publicly available speech databases, in two languages and for two types of spectral distortion.

show abstract

“…Due to this experience we were able to design most of the key modules required for the current project during its first year. The project's background and some preliminary results were published in [8]. In this paper we focus more on technical details and present the latest results achieved after processing about 75.000 archive recordings.…”

Section: Introductionmentioning

confidence: 98%

Large-scale processing, indexing and search system for Czech audio-visual cultural heritage archives

Nouza

Blavka

Žďánský

et al. 2012

2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

This paper describes a complex system developed for processing, indexing and accessing data collected in large audio and audio-visual archives that make an important part of Czech cultural heritage. Recently, the system is being applied to the Czech Radio archive, namely to its oral history segment with more than 200.000 individual recordings covering almost ninety years of broadcasting in the Czech Republic and former Czechoslovakia. The ultimate goals are a) to transcribe a significant portion of the archive -with the support of speech, speaker and language recognition technology, b) index the transcriptions, and c) make the audio and text files fully searchable. So far, the system has processed and indexed over 75.000 spoken documents. Most of them come from the last two decades, but the recent demo collection includes also a series of presidential speeches since 1934. The full coverage of the archive should be available by the end of 2014.

show abstract

Voice Technology to Enable Sophisticated Access to Historical Audio Archive of the Czech Radio

Cited by 14 publications

References 6 publications

Combining Manual and Automatic Annotation of a Learner Corpus

Combining Manual and Automatic Annotation of a Learner Corpus

Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech

Large-scale processing, indexing and search system for Czech audio-visual cultural heritage archives

Contact Info

Product

Resources

About