Franco Ravera

Analysis and improvement of the partial distance search algorithm

The partial distance search algorithm (PDS) introduced for reducing the computational complexity of the nearest neighbor search in vector quantization is analyzed. In particular, a detailed analysis of the computational savings that can be obtained by minor modifications to this algorithm is performed. A dynamic programming procedure is proposed that automatically determines how often the comparison with the current minimum distance has to be done in order to minimize the expected global cost of the search. The number and position of the comparisons within the distance evaluation loop depend on the ratio of the cost of a comparison operation to that of the partial distance evaluation. It is shown that the two costs are comparable for RISC (reduced instruction set computer) processors, and a 25% speedup with respect to the PDS algorithm is reported for 24 dimension feature vectors used in a continuous-density HMM (hidden Markov model) system with 16 Gaussian mixtures per state.<<ETX>>

Connected digit recognition using short and long duration models

We show that accurate HMMs for connected word recognition can be obtained without context dependent modeling and discriminative training. We train two HMMs for each word that have the same, standard, left to right topology with the possibility of skipping once state, but each model has a different number of states, automatically selected. The two models account for different speaking rates that occur not only in different utterances of the speakers, but also within a connected word utterance of the same speaker. This simple modeling technique has been applied to connected digit recognition using the adult speaker portion of the TI/NIST corpus giving the best results reported so far for this database. It has also been tested on telephone speech using long sequences of Italian digits (credit card numbers), giving better results with respect to classical models with a larger number of densities.

Using word temporal structure in HMM speech recognition

Isolated word speech recognizers with fixed vocabularies are often used to provide vocal services through the telephone line. The paper illustrates a simple postprocessing approach that allows the hypotheses produced by a hidden Markov model recognizer to be rescored taking into account the global temporal structure of the pronounced words. Our approach does not directly rely on state/word duration modeling. It models, instead, the global time variations of the spectral features of each word and their correlation in time: two important perceptual cues that are only partially exploited by standard HMMs. This method has been evaluated using three isolated word speaker independent systems with vocabulary of different size and complexity. We show that, with minimal overhead, the recognition performance improves not only for small vocabulary recognition systems such as the isolated digit one, or for the recognition of 26 Italian spelling names, but also for a system with a 475 city name vocabulary included in a vocal service that provides information about the main railway connections.

Segmental search for continuous speech recognition

The paper illustrates a search strategy for continuous speech recognition based on the recently developed fast segmental Viterbi algorithm (FSVA), a new search strategy particularly effective for very large vocabulary word recognition. The FSVA search has been extended to deal with continuous speech using a network that merges a general lexical tree and a set of bigram subtrees generated on demand during the search. Results are given for a 751-words speaker independent spontaneous speech recognizer of a railway timetable inquiry application, managed by a dialog system. Preliminary tests have been performed on the Wall Street Journal 5K words 1992 evaluation set.