Supervised and unsupervised learning of multidimensional acoustic categories.
نویسندگان
چکیده
منابع مشابه
Supervised and unsupervised learning of multidimensional acoustic categories.
Learning to recognize the contrasts of a language-specific phonemic repertoire can be viewed as forming categories in a multidimensional psychophysical space. Research on the learning of distributionally defined visual categories has shown that categories defined over 1 dimension are easy to learn and that learning multidimensional categories is more difficult but tractable under specific task ...
متن کاملLightly supervised and unsupervised acoustic model training
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe unrestricted broadcast news audio data with a word error of about 20%. However, acoustic model development for these recognizers relies on the availability of large amounts of manually transcribed training data. Obtaining such data is both time-consu...
متن کاملUnsupervised versus supervised training of acoustic models
In this paper we reports unsupervised training experiments we have conducted on large amounts of the English Fisher conversational telephone speech. A great amount of work has been reported on unsupervised training, but the major difference of this work is that we compared behaviors of unsupervised training with supervised training on exactly the same data. This comparison reveals surprising re...
متن کاملSupervised and unsupervised learning of multidimensionally varying non-native speech categories
The acquisition of novel phonetic categories is hypothesized to be affected by the distributional properties of the input, the relation of the new categories to the native phonology, and the availability of supervision (feedback). These factors were examined in four experiments in which listeners were presented with novel categories based on vowels of Dutch. Distribution was varied such that th...
متن کاملSplitting the Unsupervised and Supervised Components of Semi-Supervised Learning
In this paper we investigate techniques for semi-supervised learning that split their unsupervised and supervised components — that is, an initial unsupervised phase is followed by a supervised learning phase. We first analyze the relative value of labeled and unlabeled data. We then present methods that perform “split” semi-supervised learning and show promising empirical results.
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: Journal of Experimental Psychology: Human Perception and Performance
سال: 2009
ISSN: 1939-1277,0096-1523
DOI: 10.1037/a0015781