On parameter filtering in continuous subword-unit-based speech recognition
نویسندگان
چکیده
Simple IIR or FIR filters have been widely used in isolated or connected word recognition tasks to filter the time sequence of speech spectral parameters, since, despite their simplicity, they significantly improve recognition performance. Those filters, when applied to continuous speech recognition, where phoneme-sized modelling units are used, induce spectral transition spreading and a cross-boundary effect. In this work, we show how the use of context-dependent units reduces the side effects of the filters and may result in improved recognition performance. When dynamic parameters are not used, filtering seems to be especially useful, even for clean speech, and when they are, filters do well under unmatched training and testing conditions.
منابع مشابه
Articulatory feature based continuous speech recognition using probabilistic lexical modeling
Phonological studies suggest that the typical subword units such as phones or phonemes used in automatic speech recognition systems can be decomposed into a set of features based on the articulators used to produce the sound. Most of the current approaches to integrate articulatory feature (AF) representations into an automatic speech recognition (ASR) system are based on deterministic knowledg...
متن کاملIsadora | a Speech Modelling Network Based on Hidden Markov Models
In this paper we present the ISADORA system which provides highly exible speech recognition based on HMM technology together with an hierarchical representation of speech units. Markov model topologies, subword unit inventories, regular grammars expressed in nite-state or phrase structure style, and even the analysis tasks themselves are explicitly represented by the nodes of a large speech uni...
متن کاملVocabulary Extension Recognition System for a based Speaker - Adaptive on CVC Units
For speech recognition with large vocabularies, a user should not be burdened with having to train several thousand words explicitly. Therefore, it proves extremely useful to provide a means for easy vocabulary generation and enlargement from written text input. Applying a set of appropriately defined rules, the orthography of a lexicon item is first transcribed into the phonetic symbols of the...
متن کاملSubword-based approaches for spoken document retrieval
This paper explores approaches to the problem of spoken document retrieval (SDR), which is the task of automatically indexing and then retrieving relevant items from a large collection of recorded speech messages in response to a user specified natural language text query. We investigate the use of subword unit representations for SDR as an alternative to words generated by either keyword spott...
متن کاملSpeech Recognition Using Demi-Syllable Neural Prediction Model
The Neural Prediction Model is the speech recognition model based on pattern prediction by multilayer perceptrons. Its effectiveness was confirmed by the speaker-independent digit recognition experiments. This paper presents an improvement in the model and its application to large vocabulary speech recognition, based on subword units. The improvement involves an introduction of "backward predic...
متن کامل