Exploiting variable-width features in large vocabulary speech recognition

The use of variable-width features (prosodics, broad structural information etc.) in large vocabulary speech recognition systems is discussed. Although the value of this sort of information has been recognized in the past, previous approaches have not been widely used in speech systems because either they have not been robust enough for realistic, large vocabulary tasks or they have been limited to certain recognizer architectures. A framework for the use of variable-width features is presented which employs the N-Best algorithm with the features being applied in a post-processing phase. The framework is flexible and widely applicable, giving greater scope for exploitation of the features than previous approaches. Large vocabulary speech recognition experiments using TIMIT show that the application of variable-width features has potential benefits.

Extending noise robust structured support vector machines to larger vocabulary tasks

This paper describes a structured SVM framework suitable for noise-robust medium/large vocabulary speech recognition. Several theoretical and practical extensions to previous work on small vocabulary tasks are detailed. The joint feature space based on word models is extended to allow context-dependent triphone models to be used. By interpreting the structured SVM as a large margin log-linear model, illustrates that there is an implicit assumption that the prior of the discriminative parameter is a zero mean Gaussian. However, depending on the definition of likelihood feature space, a non-zero prior may be more appropriate. A general Gaussian prior is incorporated into the large margin training criterion in a form that allows the cutting plan algorithm to be directly applied. To further speed up the training process, 1-slack algorithm, caching competing hypothesis and parallelization strategies are also proposed. The performance of structured SVMs is evaluated on noise corrupted medium vocabulary speech recognition task: AURORA 4. © 2011 IEEE.

Development of the 2003 CU-HTK conversational telephone speech transcription system

This paper describes the development of the 2003 CU-HTK large vocabulary speech recognition system for Conversational Telephone Speech (CTS). The system was designed based on a multi-pass, multi-branch structure where the output of all branches is combined using system combination. A number of advanced modelling techniques such as Speaker Adaptive Training, Heteroscedastic Linear Discriminant Analysis, Minimum Phone Error estimation and specially constructed Single Pronunciation dictionaries were employed. The effectiveness of each of these techniques and their potential contribution to the result of system combination was evaluated in the framework of a state-of-the-art LVCSR system with sophisticated adaptation. The final 2003 CU-HTK CTS system constructed from some of these models is described and its performance on the DARPA/NIST 2003 Rich Transcription (RT-03) evaluation test set is discussed.

Vision-based global localization using a visual vocabular

This paper presents a novel coarse-to-fine global localization approach that is inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by SIFT descriptors are used as natural land-marks. These descriptors are indexed into two databases: an inverted index and a location database. The inverted index is built based on a visual vocabulary learned from the feature descriptors. In the location database, each location is directly represented by a set of scale invariant descriptors. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the inverted index is fast but not accurate enough; whereas localization from the location database using voting algorithm is relatively slow but more accurate. The combination of coarse and fine stages makes fast and reliable localization possible. In addition, if necessary, the localization result can be verified by epipolar geometry between the representative view in database and the view to be localized. Experimental results show that our approach is efficient and reliable. ©2005 IEEE.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. In normal cross adaptation it is assumed that useful diversity among systems exists only at acoustic level. However, complimentary features among complex LVCSR systems also manifest themselves in other layers of modelling hierarchy, e.g., subword and word level. It is thus interesting to also cross adapt language models (LM) to capture them. In this paper cross adaptation of multi-level LMs modelling both syllable and word sequences was investigated to improve LVCSR system combination. Significant error rate gains up to 6.7% rel. were obtained over ROVER and acoustic model only cross adaptation when combining 13 Chinese LVCSR subsystems used in the 2010 DARPA GALE evaluation. © 2010 ISCA.

Understanding function and function-to-form evolution

This is a report on a workshop held at Cambridge University Engineering Design Centre, 17-10 June 1992. This workshop was held to discuss the issue of 'function' and 'function-to-form' evolution in mechanical design. The authors organised this workshop as they felt that their understanding of these topics was incomplete and that discussions between researchers might help to clarify some key issues.

The topic chosen for the workshop proved to be a stimulating one. The term 'function' is part of a designer's daily vocabulary, however there is poor agreement about its definition. In order to develop computer systems to support product evolution, a precise definition is required. Further the value of 'function' and 'function-to-form' evolution as a good choice of workshop topic is evident from the lack of firm conclusions that resulted from the sessions. This lack of consensus made for lively discussion and left participants questioning many of their preconceived ideas.

Attendance at the workshop was by invitation only. A list of the participants (not all those invited could attend due to time and financial constraints) is given in Appendix 1.

Rule-based grapheme-to-phoneme method for the Greek

This paper describes a trainable method for generating letter to sound rules for the Greek language, for producing the pronunciation of out-of-vocabulary words. Several approaches have been adopted over the years for grapheme-to-phoneme conversion, such as hand-seeded rules, finite state transducers, neural networks, HMMs etc, nevertheless it has been proved that the most reliable method is a rule-based one. Our approach is based on a semi-automatically pre-transcribed lexicon, from which we derived rules for automatic transcription. The efficiency and robustness of our method are proved by experiments on out-of-vocabulary words which resulted in over than 98% accuracy on a word-base criterion.