Abstract
Spoken term detection (STD) aims at retrieving data from a speech repository given a textual representation of the search term. Nowadays, it is receiving much interest due to the large volume of multimedia information. STD differs from automatic speech recognition (ASR) in that ASR is interested in all the terms/words that appear in the speech data, whereas STD focuses on a selected list of search terms that must be detected within the speech data. This paper presents the systems submitted to the STD ALBAYZIN 2014 evaluation, held as a part of the ALBAYZIN 2014 evaluation campaign within the context of the IberSPEECH 2014 conference. This is the first STD evaluation that deals with Spanish language. The evaluation consists of retrieving the speech files that contain the search terms, indicating their start and end times within the appropriate speech file, along with a score value that reflects the confidence given to the detection of the search term. The evaluation is conducted on a Spanish spontaneous speech database, which comprises a set of talks from workshops and amounts to about 7 h of speech. We present the database, the evaluation metrics, the systems submitted to the evaluation, the results, and a detailed discussion. Four different research groups took part in the evaluation. Evaluation results show reasonable performance for moderate out-of-vocabulary term rate. This paper compares the systems submitted to the evaluation and makes a deep analysis based on some search term properties (term length, in-vocabulary/out-of-vocabulary terms, single-word/multi-word terms, and in-language/foreign terms).
Highlights
The enormous amount of information stored in audio and audiovisual repositories promotes the development of efficient methods that aim at retrieving the stored information
The best performance on training/development data is obtained by the WL-word error rate (WER)-Kaldi system, whereas the best performance on test data is obtained by the WL-Kaldi system
Paired t-tests show that the best performance of the WL-WER-Kaldi system on training/development data is statistically significant compared to the rest of the systems (p < 10−10) for ATWV
Summary
The enormous amount of information stored in audio and audiovisual repositories promotes the development of efficient methods that aim at retrieving the stored information. Tejedor et al EURASIP Journal on Audio, Speech, and Music Processing (2015) 2015:21 on different speech technologies (e.g., speech segmentation [34], speaker diarization [35], language recognition [36], query-by-example spoken term detection [37], and speech synthesis [38] in the ALBAYZIN 2010 and 2012 evaluation campaigns). This year, this campaign has been held during the IberSPEECH 2014 conference [39].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have