Publications

Refine Results

(Filters Applied) Clear All

By

Speaker verification using text-constrained Gaussian mixture models

May 13, 2002
  |
Conference Paper
Author:
Douglas E. Sturim
…
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. I, 13-17 May 2002, pp. I-677 - I-680.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

In this paper we present an approach to close the gap between text-dependent and text-independent speaker verification performance. Text-constrained GMM-UBM systems are created using word segmentations produced by a LVCSR system on conversational speech allowing the system to focus on speaker differences over a constrained set of acoustic units. Results on the 2001 NiST extended data task show this approach can be used to produce an equal error rate of < 1%.
READ LESS

Summary

In this paper we present an approach to close the gap between text-dependent and text-independent speaker verification performance. Text-constrained GMM-UBM systems are created using word segmentations produced by a LVCSR system on conversational speech allowing the system to focus on speaker differences over a constrained set of acoustic units. Results...

READ MORE
Speaker verification using text-constrained Gaussian mixture models

Speech enhancement based on auditory spectral change

May 13, 2002
  |
Conference Paper
Author:
Thomas F. Quatieri
…
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. I, Speech Processing Neural Networks for Signal Processing, 13-17 May 2002, pp. I-257 - I-260.
Topic:
speech enhancement
R&D area:
R&D group:

Summary

In this paper, an adaptive approach to the enhancement of speech signals is developed based on auditory spectral change. The algorithm is motivated by sensitivity of aural biologic systems to signal dynamics, by evidence that noise is aurally masked by rapid changes in a signal, and by analogies to these two aural phenomena in biologic visual processing. Emphasis is on preserving nonstationarity, i.e., speech transient and time-varying components, such as plosive bursts, formant transitions, and vowel onsets, while suppressing additive noise. The essence of the enhancement technique is a Wiener filter that uses a desired signal spectrum whose estimation adapts to stationarity of the measured signal. The degree of stationarity is derived from a signal change measurement, based on an auditory spectrum that accentuates change in spectral bands. The adaptive filter is applied in an unconventional overlap-add analysis/synthesis framework, using a very short 4-ms analysis window and a 1-ms frame interval. In informal listening, the reconstructions are judged to be "crisp" corresponding to good temporal resolution of transient and rapidly-moving speech events.
READ LESS

Summary

In this paper, an adaptive approach to the enhancement of speech signals is developed based on auditory spectral change. The algorithm is motivated by sensitivity of aural biologic systems to signal dynamics, by evidence that noise is aurally masked by rapid changes in a signal, and by analogies to these...

READ MORE
Speech enhancement based on auditory spectral change

Speaker recognition from coded speech and the effects of score normalization

November 4, 2001
  |
Conference Paper
Author:
Robert B. Dunn
…
Published in:
Proc. Thirty-Fifth Asilomar Conf. on Signals, Systems and Computers, Vol. 2, 4-7 November 2001, pp. 1562-1567.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments used standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss in recognition performance for toll quality speech coders and slightly more loss when lower quality speech coders are used. Speaker recognition from coded speech using handset dependent score normalization and test score normalization are examined. Both types of score normalization significantly improve performance, and can eliminate the performance loss that occurs when there is a mismatch between training and testing conditions.
READ LESS

Summary

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments used standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss...

READ MORE
Speaker recognition from coded speech and the effects of score normalization

Speaker recognition from coded speech in matched and mismatched conditions

June 18, 2001
  |
Conference Paper
Author:
Robert B. Dunn
…
Published in:
Proc. 2001: A Speaker Odyssey, The Speaker Recognition Workshop, 18-22 June 2001, pp. 115-20.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments use standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss in recognition performance for toll quality speech coders and slightly more loss when lower quality speech coders are used. Speaker recognition from coded speech using handset dependent score normalization is examined, and we find that this significantly improves performance, particularly when there is a mismatch between training and testing conditions.
READ LESS

Summary

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments use standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss...

READ MORE
Speaker recognition from coded speech in matched and mismatched conditions

The Lincoln speaker recognition system: NIST EVAL2000

October 16, 2000
  |
Conference Paper
Author:
Douglas A. Reynolds
…
Published in:
6th Int. Conf. on Spoken Language, ICSLP, 16-20 October 2000.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

This paper presents an overview of the Lincoln Laboratory systems fielded for the 2000 NIST speaker recognition evaluation (SRE00). In addition to the standard one-speaker detection tasks, this year's evaluation, as in 1999, included multi-speaker spokes dealing with detection, tracking and segmentation. The design approach for the Lincoln system in SRE00 was to develop a set of core one-speaker detection and multi-speaker clustering tools that could be applied to all the tasks. This paper will describe these core systems, how they are applied to the SRE00 tasks and the results they produce. Additionally, a new channel normalization technique known as handset-dependent test-score norm (HTnorm) is introduced.
READ LESS

Summary

This paper presents an overview of the Lincoln Laboratory systems fielded for the 2000 NIST speaker recognition evaluation (SRE00). In addition to the standard one-speaker detection tasks, this year's evaluation, as in 1999, included multi-speaker spokes dealing with detection, tracking and segmentation. The design approach for the Lincoln system in...

READ MORE
The Lincoln speaker recognition system: NIST EVAL2000

Speaker recognition using G.729 speech codec parameters

June 5, 2000
  |
Conference Paper
Author:
Thomas F. Quatieri
…
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, Vol. II, 5-9 June 2000, pp. 1089-1092.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

Experiments in Gaussian-mixture-model speaker recognition from mel-filter bank energies (MFBs) of the G.729 codec all-pole spectral envelope, showed significant performance loss relative to the standard mel-cepstral coefficients of G.729 synthesized (coded) speech. In this paper, we investigate two approaches to recover speaker recognition performance from G.729 parameters, rather than deriving cepstra from MFBs of an all-pole spectrum. Specifically, the G.729 LSFs are converted to "direct" cepstral coefficients for which there exists a one-to-one correspondence with the LSFs. The G.729 residual is also considered; in particular, appending G.729 pitch as a single parameter to the direct cepstral coefficients gives further performance gain. The second nonparametric approach uses the original MFB paradigm, but adds harmonic striations to the G.729 all-pole spectral envelope. Although obtaining considerable performance gains with these methods, we have yet to match the performance of G.729 synthesized speech, motivating the need for representing additional fine structure of the G.729 residual.
READ LESS

Summary

Experiments in Gaussian-mixture-model speaker recognition from mel-filter bank energies (MFBs) of the G.729 codec all-pole spectral envelope, showed significant performance loss relative to the standard mel-cepstral coefficients of G.729 synthesized (coded) speech. In this paper, we investigate two approaches to recover speaker recognition performance from G.729 parameters, rather than deriving...

READ MORE
Speaker recognition using G.729 speech codec parameters

Approaches to speaker detection and tracking in conversational speech

January 1, 2000
  |
Journal Article
Author:
Robert B. Dunn
…
Published in:
Digit. Signal Process., Vol. 10, No. 1, January/April/July, 2000, pp. 93-112. (Fifth Annual NIST Speaker Recognition Workshop, 3-4 June 1999.)
Topic:
speaker recognition
R&D area:
R&D group:

Summary

Two approaches to detecting and tracking speakers in multispeaker audio are described. Both approaches use an adapted Gaussian mixture model, universal background model (GMM-UBM) speaker detection system as the core speaker recognition engine. In one approach, the individual log-likelihood ratio scores, which are produced on a frame-by-frame basis by the GMM-UBM system, are used to first partition the speech file into speaker homogenous regions and then to create scores for these regions. We refer to this approach as internal segmentation. Another approach uses an external segmentation algorithm, based on blind clustering, to partition the speech file into speaker homogenous regions. The adapted GMM-UBM system then scores each of these regions as in the single-speaker recognition case. We show that the external segmentation system outperforms the internal segmentation system for both detection and tracking. In addition, we show how different components of the detection and tracking algorithms contribute to the overall system performance.
READ LESS

Summary

Two approaches to detecting and tracking speakers in multispeaker audio are described. Both approaches use an adapted Gaussian mixture model, universal background model (GMM-UBM) speaker detection system as the core speaker recognition engine. In one approach, the individual log-likelihood ratio scores, which are produced on a frame-by-frame basis by the...

READ MORE
Approaches to speaker detection and tracking in conversational speech

Speaker verification using adapted Gaussian mixture models

January 1, 2000
  |
Journal Article
Author:
Douglas A. Reynolds
…
Published in:
Digit. Signal Process., Vol. 10, No. 1-3, January/April/July, 2000, pp. 19-41. (Fifth Annual NIST Speaker Recognition Workshop, 3-4 June 1999.)
Topic:
speaker recognition
R&D area:
R&D group:

Summary

In this paper we describe the major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance is also described and discussed. Finally, representative performance benchmarks and system behavior experiments on NIST SRE corpora are presented.
READ LESS

Summary

In this paper we describe the major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background...

READ MORE
Speaker verification using adapted Gaussian mixture models

Speaker and language recognition using speech codec parameters

September 5, 1999
  |
Conference Paper
Author:
Thomas F. Quatieri
…
Published in:
EUROSPEECH 99, 5-10 September 1999.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

In this paper, we investigate the effect of speech coding on speaker and language recognition tasks. Three coders were selected to cover a wide range of quality and bit rates: GSM at 12.2 kb/s, G.729 at 8 kb/s, and G.723.1 at 5.3 kb/s. Our objective is to measure recognition performance from either the synthesized speech or directly from the coder parameters themselves. We show that using speech synthesized from the three codecs, GMM-based speaker verification and phone-based language recognition performance generally degrades with coder bit rate, i.e., from GSM to G.729 to G.723.1, relative to an uncoded baseline. In addition, speaker verification for all codecs shows a performance decrease as the degree of mismatch between training and testing conditions increases, while language recognition exhibited no decrease in performance. We also present initial results in determining the relative importance of codec system components in their direct use for recognition tasks. For the G.729 codec, it is shown that removal of the post- filter in the decoder helps speaker verification performance under the mismatched condition. On the other hand, with use of G.729 LSF-based mel-cepstra, performance decreases under all conditions, indicating the need for a residual contribution to the feature representation.
READ LESS

Summary

In this paper, we investigate the effect of speech coding on speaker and language recognition tasks. Three coders were selected to cover a wide range of quality and bit rates: GSM at 12.2 kb/s, G.729 at 8 kb/s, and G.723.1 at 5.3 kb/s. Our objective is to measure recognition performance...

READ MORE
Speaker and language recognition using speech codec parameters

Embedded dual-rate sinusoidal transform coding

September 10, 1997
  |
Conference Paper
Author:
Elliot Singer
…
Published in:
Proc. IEEE Workshop on Speech Coding for Telecommunications Proc.: Back to Basics: Attacking Fundamental Problems in Speech Coding, 7-10 September 1997, pp. 33-34.
Topic:
speech processing
R&D area:
R&D group:

Summary

This paper describes the development of a dual-rate Sinusoidal Transformer Coder in which a 2400 b/s coder is embedded as a separate packet in the 4800 b/s bit stream. The underlying coding structure provides the flexibility necessary for multirate speech coding and multimedia applications.
READ LESS

Summary

This paper describes the development of a dual-rate Sinusoidal Transformer Coder in which a 2400 b/s coder is embedded as a separate packet in the 4800 b/s bit stream. The underlying coding structure provides the flexibility necessary for multirate speech coding and multimedia applications.

READ MORE
Embedded dual-rate sinusoidal transform coding
11-20 of 26