‘Bunsetsu’ Spotting-based Japanese Continuous Speech Recognition
نویسندگان
چکیده
منابع مشابه
Speech recognition using error spotting
Spontaneous conversational phone-call speech databases are di cult to recognize because of the large variation of speech rates, of pronunciations as well as noises, of acoustic degradations from the telephone channel, and of an unpredictable non-grammatical language structure including many random phenomena. Each cause of misrecognition can be addressed separately; however there is still no sat...
متن کاملPhoneme Based Acoustics Keyword Spotting in Informal Continuous Speech
This paper describes several ways of keywords spotting (KWS), based on Gaussian mixture (GM) hidden Markov modelling (HMM). Context-independent and dependent phoneme models are used in our system. The system was trained and evaluated on informal continuous speech. We used different complexities of KWS recognition networks and different types of phoneme models. The impact of these parameters on ...
متن کاملPhoneme Probability Presentation of Continuous Speech based on Phoneme Spotting
SUMMARY This paper describes a new presentation of continuous speech in terms of the probability of all phoneme types as a function of time. The presentation is called a phoneme probability presentation (PPP) and can be used for phoneme recognition of continuous speech. As a technique ,,0 produce the PPP, we have employed hidden Markov models (HMM) with time duration information. This informati...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEJ Transactions on Electronics, Information and Systems
سال: 1988
ISSN: 0385-4221,1348-8155
DOI: 10.1541/ieejeiss1987.108.10_826