Several attempts to improve recognition accuracy with the use of supervised clustering techniques are described. These techniques modify the distance metric and/or the clustering procedure in a discrete hidden Markov model recognition system in an attempt to improve phonetic modeling. Three techniques considered are linear discriminant analysis, a hierarchical supervised vector quantization technique, and Kohonen's LVQ2 technique. All experiments were performed on the DARPA resource management speech corpus using the BBN BYBLOS system. Even though the techniques improved the phonetic recognition capability of the vector quantization, the overall word and sentence recognition accuracy did not improve.>

A word-spotting system using Gaussian hidden Markov models is presented. Several aspects of this problem are investigated. Specifically, results are reported on the use of various signal processing and feature transformation techniques. The authors have observed that performance can be greatly affected by the choice of features used, the covariance structure of the Gaussian models, and transformations based on energy and feature distributions. Due to the open-set nature of the problem, the specific techniques for modeling out-of-vocabulary speech and the choice of scoring metric can have a significant effect on performance.>

In previous papers, we have described the segment vocoder, which transmits intelligible speech at 300 b/s in speaker-independent mode, i.e., new users need not train the system. As expected for vector quantizers, the storage and computational requirements of the segment vocoder are significantly larger than those of the standard LPC-10 vocoder. In this paper, we describe methods for reducing computational and storage requirements of the segment vocoder and present an algorithm that is implementable in real-time on hardware containing several Digital Signal Processing chips. The DRT score of the simplified algorithm is 78%.

We consider methods for text-independent speaker identification that deal with the variability in the data introduced by unknown telephone channels. The methods investigated include probabilistic channel modeling, a channel-invariant model and a modified-Gaussian model. The methods are described and then evaluated with experiments conducted with a twenty speaker database of long distance telephone calls.

In this research, we developed and tested a variety of new objective measures for automatically evaluating pitch extractors for use in narrowband speech coders. For automatic computation of an accurate, reference pitch contour required by the objective measures, we modified an existing algorithm that uses the subglottal signal recorded simultaneously with the speech signal. To test and validate the objective measures, we conducted formal subjective speech quality tests, which involved five pitch extractors; a specially selected speech database of sentences that are likely to cause pitch and voicing errors; and two 2.4 kbit/s speech coders, the LPC coder and the harmonic deviations coder, each operating in clear or no noise and in Air Borne Command Post noise. Results obtained by correlating the objective scores with the mean subjective rating scores show that several of our objective measures produce consistently excellent correlation (0.9 - 0.995) for both coders and under both acoustic background conditions.

We consider in this paper the problem of developing and testing a procedure for objective evaluation of the speech quality of real-time speech coders. We validate this evaluation procedure by computing the objective quality scores over a test bed of five mediumband and narrowband real-time speech coders and correlating the scores with subjective judgments generated by the Diagnostic Acceptability Measure test. We report on the performance of several published objective measures. Also, we describe and suggest solution approaches to two related problems: synchronize in time a real-time coder's output with its input, and design a database of input-speech sentences to be used in objective speech quality evaluation. We present various experimental results of this ongoing work.

This paper presents the development, study, and experimental results of a narrowband speech coder called Harmonic Deviations (HDV) Vocoder. The HDV coder is based on the LPC vocoder, and it transmits additional information over and above the data transmitted by the LPC vocoder, in the form of deviations between the speech spectrum and the LPC all-pole model spectrum at a selected set of frequencies. At the receiver, the spectral deviations are used to generate the excitation signal for the all-pole synthesis filter. The paper describes and compares several methods for extracting the spectral deviations from the speech signal and for encoding them. To limit the bit-rate of the HDV coder to 2.4 kb/s the paper discusses several methods including orthogonal transformation and minimum-mean-square-error scalar quantization of log area ratios, two-stage vector-scalar quantization, and variable frame rate transmission. The paper also presents the results of speech-quality optimization of the HDV coder at 2.4 kb/s. Both noisefree and noisy channel applications are considered. The resulting HDV coders yield noticeable improvement in speech quality over LPC vocoders.

This paper describes the design of a baseband LPC coder that transmits speech over 9.6 kbit/s (kilobit/second) synchronous channels with random bit errors of up to 1 percent. Presented are the results of our investigation of a number of aspects of the baseband LPC coder with the goal of maximizing the quality of the transmitted speech. Important among these aspects are: bandwidth of the baseband, coding of the baseband residual, high-frequency regeneration, and error protection of important transmission parameters. The paper discusses these and other issues, presents the results of speech-quality tests conducted during the various stages of optimization, and describes the details of the optimized speech coder. This optimized speech coding algorithm has been implemented as a real-time full-duplex system on an array processor. Informal listening tests of the real-time coder have shown that the coder produces good speech quality in the absence of channel bit errors and introduces only a slight degradation in quality for channel bit error rates of up to 1 percent.

This paper presents the results of our optimization study of 16 kb/s APC coders operating over noisy channels. With the objective of achieving good speech quality and a robust coder performance for channel bit-error rates of up to 1%, we have investigated a number of issues including: the tradeoff between voice-data bandwidth and error-protection bandwidth; the amount of error protection for individual transmission parameters; comparison of several residual coding methods; the relative performance of the two ways of sequencing the spectral and pitch predictors; use of folded binary code for encoding the quantized residual; and smoothing of the decoded residual. Most impressive of the several interesting and useful results reported in the paper is that the final optimized, robust coder design yields speech quality that degrades only slightly as the bit-error rate is increased from 0% to 1%.

This paper presents the results of our investigation of the various aspects of baseband LPC coders with the goal of maximizing the speech quality at a transmission bit-rate of 9.6 kb/s and for channel bit-error rates of up to 1%. Important among these aspects are: baseband width, coding of baseband, high-frequency regeneration, and error protection of important transmission parameters. The paper discusses these and other issues, presents the results of speech-quality tests conducted during the various stages of optimization, and describes the details of the optimized speech coder.

This paper considers the optimization of speech quality of adaptive predictive coding (APC) systems for transmission over a synchronous 16 kb/s channel. Among the important issues included in this on-going optimization study are: comparative evaluation of several methods for adaptive coding of the APC residual; comparative testing of several methods for adaptive shaping of the spectrum of the quantization noise; and optimization of various parameter values and their bit allocation. In addition to reporting the results from this study, we report on the occurrence of "limit cycles" or regions of excessive quantization noise build-up, offer an explanation for their cause in terms of the feedback gain (or "loop gain") of the APC transmitter, and present experimental results obtained using several remedial means for this problem. Also, we report on the relative properties of different APC coder configurations. Based on the results of our optimization study to date, we present several optimized APC systems.

Recently we described a variable-frame-rate LPC vocoder designed to transmit good quality speech over 2400 bps fixed-rate noisy channels with bit-error probabilities ranging up to 5% [3]. The basic idea was to lower the data rate by transmitting LPC parameters only when speech characteristics have changed sufficiently since the last transmission, and to employ the resulting bit-rate savings for protecting important transmission data against channel noise. This paper describes our continuing efforts which have concentrated on minimizing loss of synchronization between the receiver and the transmitter. In one approach, we emphasize heavy protection of header, and rapid resynchronization. Alternatively, we apply constraints which guarantee synchronization at a cost of some freedom in the selection of data for transmission. Results from the first approach are presented; results from both methods will be compared at the conference.

This paper considers the use of voice-excited linear predictive (LPC) coders for speech transmission at a bit-rate of 9.6 kbps. In our on-going work, we study in detail the various aspects of this class of speech coders, with the goal of maximizing the speech quality at the above rate. Important among these aspects are: baseband residual versus baseband speech transmission, coding of the baseband signal, and high-frequency regeneration from the baseband. We provide a discussion of these and other issues, and indicate a number of variables that have been included in our speech-quality optimization study. Experimental results obtained to date are summarized in the paper. More complete results and conclusions will be presented at the conference.

Several methods are presented for the objective speech quality evaluation of narrowband LPC vocoders, based on a framework that we proposed at the 1976 ICASSP conference. In each method, the error in short-term spectral behavior between vocoded speech and the original is computed once every 10 ms. These errors are appropriately weighted and averaged over an utterance to produce a single objective score. Several short-term error measures, and time-weighting and averaging techniques are investigated. We evaluate the objective methods by correlating the resulting objective scores with formal subjective speech quality judgments. High correlations obtained indicate the usefulness of these methods.

While there exist methods in the literature for objectively evaluating the intelligibility of speech in the presence of stationary noise, little has been done regarding the objective evaluation of either the intelligibility or the quality of vocoded speech. We present a framework within which we have begun a step-by-step program to develop objective measures for vocoded speech quality that are consistent with results from subjective tests.

This paper considers distance measures for determining the deviation between two smoothed short-time speech spectra. Since such distance measures are employed in speech processing applications that either involve or relate to human perceptual judgment, the effectiveness of these measures will be enhanced if they provide results consistent with human speech perception. As a first step, we suggest Flanagan's results on difference limens for formant frequencies as one basis for checking the perceptual consistency of a measure. A general necessary condition for perceptual consistency is derived for a class of spectral distance measures. A class of perceptually consistent measures obtained through experimental investigations is then described, and results obtained using one such measure under Flanagan's test conditions are presented.