A corpus of Polish speech, which has been collected for the purpose of automatic speech recognition (ASR) and text-to-speech (TTS) systems applications, is presented. The corpus consists of several groups of recordings: read sentences, spoken commands, a phonetically balanced TTS training corpus, telephonic speech and others. In summary duration of recordings is above 25 h. Number of unique speakers amounts to 166. The majority of them being in an age group of 20-35 and one third of them being female. Analysis of unique word occurrence frequency in relation to larger text resources has been concluded. From them, most commonly appearing words have been found and presented. The corpus was used as training data for the ASR system. Results of cross-validation training and testing the SARMATA ASR system using our corpus have shown that phrase recognition rate is 91.9 %.
Statistics of pauses appearing in Polish as a potential source of biometry information for automatic speaker recognition were described. The usage of three main types of acoustic pauses (silent, filled and breath pauses) and syntactic pauses (punctuation marks in speech transcripts) was investigated quantitatively in three types of spontaneous speech (presentations, simultaneous interpretation and radio interviews) and read speech (audio books). Selected parameters of pauses extracted for each speaker separately or for speaker groups were examined statistically to verify usefulness of information on pauses for speaker recognition and speaker profile estimation. Quantity and duration of filled pauses, audible breaths, and correlation between the temporal structure of speech and the syntax structure of the spoken language were the features which characterize speakers most. The experiment of using pauses in speaker biometry system (using Universal Background Model and i-vectors) resulted in 30 % equal error rate. Including pause-related features to the baseline Mel-frequency cepstral coefficient system has not significantly improved its performance. In the experiment with automatic recognition of three types of spontaneous speech, we achieved 78 % accuracy, using GMM classifier. Silent pause-related features allowed distinguishing between read and spontaneous speech by extreme gradient boosting with 75 % accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.