Scandinavia INVESTIGATIONS ON CONVERSATIONAL SPEECH RECOGNITION
نویسندگان
چکیده
Automatic speech recognition of real-life conversational speech is a precondition for building natural human-centered man-machine interfaces. Being able to extract speech utterances from real-life broadcast news audio streams and transcribing them with an overall word accuracy of 83% we are still faced with the problem of transcribing true conversational speech in real-life (i.e. bad) background conditions. The switchboard task focusses on the latter problem. The paper summarizes a set of experimental investigations on the switchboard corpus using the Philips LVCSR system.
منابع مشابه
Pronunciation variant analysis using speaking style parallel corpus
To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, f...
متن کاملImproved MLLR speaker adaptation using confidence measures for conversational speech recognition
Automatic recognition of conversational speech tends to have higher word error rates (WER) than read speech. Improvements gained from unsupervised speaker adaptation methods like Maximum Likelihood Linear Regression (MLLR) [1] are reduced because of their sensitivity to recognition errors in the first pass. We show that a more detailed modeling of adaptation classes and the use of confidence me...
متن کاملThe use of cepstral means in conversational speech recognition
Environmental robustness and speaker independence are import issues of current speech recognition research. Channel and speaker adaptation methods do the best job when the adaption is done towards a normalized acoustic model. Normalization methods might make use of the model but primarily inuence the signal such that important information is kept and unwanted distortions are cancelled out. Most...
متن کاملSpeech rate effects on the processing of conversational speech across the adult life spana)
This study investigates the effect of speech rate on spoken word recognition across the adult life span. Contrary to previous studies, conversational materials with a natural variation in speech rate were used rather than lab-recorded stimuli that are subsequently artificially timecompressed. It was investigated whether older adults’ speech recognition is more adversely affected by increased sp...
متن کاملAttention shift decoding for conversational speech recognition
We introduce a novel approach to decoding in speech recognition (termed attention-shift decoding) that attempts to mimic aspects of human speech recognition responsible for robustness in processing conversational speech. Our approach is a radical departure from traditional decoding algorithms for speech recognition. We propose a method to first identify reliable regions of the speech signal and...
متن کامل