Large Vocabulary Continuous Speech Recognition: Improvements in Acoustic Modelling and Search
نویسندگان
چکیده
This paper describes the main improvements we made in two of the basic modules in our HMMbased large vocabulary speaker independent continuous speech recognition system: namely in the acoustic modelling and in the search engine. For the acoustic modelling, we paid special attention both to improved parameter tying at the density and at the state level, and to fast evaluation of the HMMs. For the search engine we developed a new and flexible system with an excellent trade-off between memoryefficiency and speed.
منابع مشابه
Spoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کاملSpeed improvement of the tree-based time asynchronous search
The IBM large vocabulary continuous speech recognition system is based on an asynchronous stack decoding scheme. This is essentially a tree search, as described in [1]. The main advantages e cient memory utilization and a single-pass search strategy make the system extremely suitable for real-time applications. This article describes further improvements in e ciency of the search method. These ...
متن کاملConditional Random Fields for Continuous Speech Recognition
Acoustic modelling based on Hidden Markov Models (HMMs) is employed by state-ofthe-art stochastic speech recognition systems. Although HMMs are a natural choice to warp the time axis and model the temporal phenomena in the speech signal, they do not model the spectral phenomena well. This is a consequence of their conditionally independent properties, which are inadequate for sequential process...
متن کاملEnsemble methods for connectionist acoustic modelling
In this paper we i n v estigate a number of ensemble methods for improving the performance of connectionist acoustic models for large vocabulary continuous speech recognition. We discuss boosting, a data selection technique which results in an ensemble of models, and mixtures-of-experts. These techniques have been applied to multi-layer perceptron acoustic models used to build a hybrid connecti...
متن کاملDynamic programming search techniques for across-word modelling in speech recognition
We describe the integration of across-word models in the RWTH large vocabulary continuous speech recognition system, where our main focus is on the realization of the acoustic recognition process. This paper presents a study of two search methods based on the priniciple of dynamic programming. For both methods we discuss the implementation details and give experimental results on the Verbmobil ...
متن کامل