Titlebook: Robust Adaptation to Non-Native Accents in Automatic Speech Recognition; Silke Goronzy Book 2002 Springer-Verlag Berlin Heidelberg 2002 Au

Inoculare

書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition影響因子(影響力)




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition影響因子(影響力)學(xué)科排名




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition網(wǎng)絡(luò)公開(kāi)度




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition網(wǎng)絡(luò)公開(kāi)度學(xué)科排名




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition被引頻次




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition被引頻次學(xué)科排名




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition年度引用




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition年度引用學(xué)科排名




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition讀者反饋




書(shū)目名稱(chēng)Robust Adaptation to Non-Native Accents in Automatic Speech Recognition讀者反饋學(xué)科排名

易于交談

絕緣

dithiolethione

Pre-processing of the Speech Data,rst,by using a microphone,the speech signal or speech waveform is converted into an electrical signal. Figure 3.1 shows a block diagram of a typical speech analysis procedure, generating . coefficients (MFCCs).The different steps are explained in the following sections.

cultivated

Speaker Adaptation,rates than SI ones. If provided with the same amount of training data, they can achieve an average word error rate a factor of two or three lower than the SI system [Woo99]. But to train SD systems, large amounts of speaker specific speech data are needed and it is often not feasible to collect this

Engaged

獨(dú)白

Pronunciation Adaptation,native data was proposed. It was shown that performance decreases if a recogniser that is optimised for native speech is exposed to non-native speech. Investigations on the ISLE database showed that including specialised non- native pronunciation variants in the dictionary can greatly improve the re

鉗子

大約冬季

改正

Phoneme Inventory,les (orthography and SAMPA transcription). Since some of the English phonemes do not exist in German a mapping to the phonetically closest German phoneme was necessary for some experiments.This mapping is given in the fourth coulmn in SectionC.2