John S. Bridle

An algorithm for connected word recognition

The principles of an efficient one-pass dynamic programming whole-word pattern matching algorithm for the recognition of spoken sequences of connected words are described. Particular attention is given to the technique for keeping track of word-sequence decisions, which may be constrained by a finite-state syntax. Some extensions of the technique are discussed.

The HDM: a segmental hidden dynamic model of coarticulation

This paper introduces a new approach to acoustic-phonetic modelling, the hidden dynamic model (HDM), which explicitly accounts for the coarticulation and transitions between neighbouring phones. Inspired by the fact that speech is really produced by an underlying dynamic system, the HDM consists of a single vector target per phone in a hidden dynamic space in which speech trajectories are produced by a simple dynamic system. The hidden space is mapped to the surface acoustic representation via a non-linear mapping in the form of a multilayer perceptron (MLP). Algorithms are presented for training of all the parameters (target vectors and MLP weights) from segmented and labelled acoustic observations alone, with no special initialisation. The model captures the dynamic structure of speech, and appears to aid a speech recognition task based on the SwitchBoard corpus.

Unsupervised speaker adaptation by probabilistic spectrum fitting

A general approach to speaker adaptation in speech recognition is described, in which speaker differences are treated as arising from a parameterized transformation. Given some unlabeled data from a particular speaker, a process is described which maximizes the likelihood of this data by estimating the transformation parameters at the same time as refining estimates of the labels. The technique is illustrated using isolated vowel spectra and phonetically motivated linear spectrum transformations and is shown to give significantly better performance than nonadaptive classification.<<ETX>>

Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech

The authors describe a novel approach to the problems of topic and speaker identification that makes use of large-vocabulary continuous speech recognition. A theoretical framework for dealing with these problems in a symmetric way is provided. Some empirical results on topic and speaker identification that have been obtained on the extensive Switchboard corpus of telephone conversations are presented.<<ETX>>

Noise compensation algorithms for use with hidden Markov model based speech recognition

A preliminary theoretical and experimental examination is made of three noise compensation techniques. The three techniques are those due to: Klatt (1976); Bridle et al (1984); and Holmes & Sedgwick (1986). The first two of these techniques have been re-interpreted for use within a hidden Markov model based recogniser. A description is given of how this was done, together with a discussion on some implementation considerations. Experimental results are given for the performance of the algorithms at various signal-to-noise ratios. The principles of recognition in noise are discussed from an implementation point of view and it is shown how the three techniques can be viewed as variations on a single theme.<<ETX>>

The ARM continuous speech recognition system

Research on continuous-speech recognition using phoneme-level hidden Markov models (HMMs) is described. The aim of the project is automatic recognition of spoken airborne reconnaissance mission (ARM) reports. The evolution of the ARM system from a simple baseline system to its current configuration is described, and a considerable number of experimental results are included. Work on alternative approaches to modeling contextual effects and on improved duration modeling is described.<<ETX>>

Topic and speaker identification via large vocabulary continuous speech recognition

In this paper we exhibit a novel approach to the problems of topic and speaker identification that makes use of a large vocabulary continuous speech recognizer. We present a theoretical framework which formulates the two tasks as complementary problems, and describe the symmetric way in which we have implemented their solution. Results of trials of the message identification systems using the Switchboard corpus of telephone conversations are reported.

Interactive digital inverse filtering and its relation to linear prediction methods

This paper is concerned with inverse filtering of the speech waveform in order to study the details of vocal tract excitation. An interactive digital inverse filtering system is described in which the advantages of previously described analogue and digital methods are combined to provide a facility with much greater convenience and power than either. Experience with this system is compared with that obtained using closed-period covariance-method linear prediction analysis. Evidence is presented to support the contention that since there is continued activity in the closed-glottis period there are definite advantages in having an interactive capability.

ZIP: A dynamic programming algorithm for time-aligning two indefinitely long utterances

In automatic speech recognition (ASR) using whole-word templates, dynamic programming (DP) is frequently used to determine the similarity of two patterns (derived from spoken words) using the optimal way of aligning their timescales. In ASR the actual timescale alignment is of secondary interest to the degree of similarity and is not normally computed. We present ZIP, a modified DP algorithm designed to compute the time alignment of two utterances of the same text of any length. By using a window and partial traceback the amount of computation and storage is kept to a modest level, although the optimality of the final path is no longer absolutely guaranteed. Uses of ZIP are given.

Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE

Given a transcription, sampling from a good model of acoustic feature trajectories should result in plausible realizations of an utterance. However, samples from current probabilistic speech synthesis systems result in low quality synthetic speech. Henter et al. have demonstrated the need to capture the dependencies between acoustic features conditioned on the phonetic labels in order to obtain high quality synthetic speech. These dependencies are often ignored in neural network based acoustic models. We tackle this deficiency by introducing a probabilistic neural network model of acoustic trajectories, trajectory RNADE, able to capture these dependencies.