-
[show abstract]
[hide abstract]
ABSTRACT: We describe recent progress in the field of prosodic modeling for speaker verification. In a previous paper, we proposed a technique for modeling syllable-based prosodic features that uses a multinomial subspace model for feature extraction and within-class covariance normalization or linear discriminant analysis for session variability compensation. In this paper, we show that performance can be significantly improved with the use of probabilistic linear discriminant analysis (PLDA) for session variability compensation. This system does not require score normalization. We report an equal error rate below 7% on a NIST 2008 task. To our knowledge, this is the best reported result to date for a prosodic system for speaker recognition. Fusion of this system with a state-of-the-art acoustic baseline system yields 10% relative improvement in the new detection cost function (DCF) as defined by NIST.
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on; 06/2011 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The SRI speaker recognition system for the 2010 NIST speaker recognition evaluation (SRE) incorporates multiple subsystems with a variety of features and modeling techniques. We describe our strategy for this year's evaluation, from the use of speech recognition and speech segmentation to the individual system descriptions as well as the final combination. Our results show that under most conditions, the cepstral systems tend to perform the best, but that other, non-cepstral systems have the most complementarity. The combination of several subsystems with the use of adequate side information gives a 35% improvement on the standard telephone condition. We also show that a constrained cepstral system based on nasal syllables tends to be more robust to vocal effort variabilities.
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on; 06/2011 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Prosodic information has been successfully used for speaker recognition for more than a decade. The best-performing prosodic system to date has been one based on features extracted over syllables obtained automatically from speech recognition output. The features are then transformed using a Fisher kernel, and speaker models are trained using support vector machines (SVMs). Recently, a simpler version of these features, based on pseudo-syllables was shown to perform well when modeled using joint factor analysis (JFA). In this work, we study the two modeling techniques for the simpler set of features. We show that, for these features, a combination of JFA systems for different sequence lengths greatly outperforms both original modeling methods. Furthermore, we show that the combination of both methods gives significant improvements over the best single system. Overall, a performance improvement of 30% in the detection cost function (DCF) with respect to the two previously published methods is achieved using very simple strategies.
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on; 04/2010 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The goal of this work was to explore the optimization of the feature extraction module (front-end) parameters to improve bird species recognition. We explored optimizing the spectral and temporal parameters of a Mel cepstrum feature-based front-end, starting from common parameter values used in speech processing experiments. These features were modeled using a Gaussian mixture model (GMM) system. We found an important improvement when increasing the spectral bandwidth and increasing the number of filter banks. We found no improvement when switching the filter bank distribution from the perceptually based Mel frequency scale to a linear frequency scale. In addition, no improvement was found when we either reduced or increased the time resolution. On the other hand, we found that the best time resolution is species dependent. We did find great improvements from a species-specific combination of different front-ends with different time resolutions relative to using the same front-end time resolution for all species.
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on; 04/2010 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The SRI speaker recognition system for the 2008 NIST speaker recognition evaluation (SRE) incorporates a variety of models and features, both cepstral and stylistic. We highlight the improvements made to specific subsystems and analyze the performance of various subsystem combinations in different data conditions. We show the importance of language and nativeness conditioning, as well as the role of ASR for speaker verification.
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on; 05/2009 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We investigate several feature normalization and scaling approaches for use in speaker verification based on support vector machines. We are particularly interested in methods that are "knowledge-free" and work for a variety of features, leading us to investigate MLLR transforms, phone N-grams, prosodic sequences, and word N-gram features. Normalization methods studied include mean/variance normalization, TFLLR and TFLOG scaling, and a simple nonparametric approach: rank-normalization. We find that rank-normalization is uniformly competitive with other methods, and improves upon them in many cases.
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on; 05/2008 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Recent studies in speaker recognition have shown that score- level combination of subsystems can yield significant performance gains over individual subsystems. We explore the use of auxiliary information to aid the combination procedure. We propose a modified linear logistic regression procedure that conditions combination weights on the auxiliary information. A regularization procedure is used to control the complexity of the extended model. Several auxiliary features are explored. Results are presented for data from the 2006 NIST speaker recognition evaluation (SRE). When an estimated degree of nonnativeness for the speaker is used as auxiliary information, the proposed combination results in a 15% relative reduction in equal error rate over methods based on standard linear logistic regression, support vector machines, and neural networks.
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on; 05/2008 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We present a new modeling approach for speaker recognition that uses the maximum-likelihood linear regression (MLLR) adaptation transforms employed by a speech recognition system as features for support vector machine (SVM) speaker models. This approach is attractive because, unlike standard frame-based cepstral speaker recognition models, it normalizes for the choice of spoken words in text-independent speaker verification without data fragmentation. We discuss the basics of the MLLR-SVM approach, and show how it can be enhanced by combining transforms relative to multiple reference models, with excellent results on recent English NIST evaluation sets. We then show how the approach can be applied even if no full word-level recognition system is available, which allows its use on non-English data even without matching speech recognizers. Finally, we examine how two recently proposed algorithms for intersession variability compensation perform in conjunction with MLLR-SVM.
IEEE Transactions on Audio Speech and Language Processing 10/2007; · 1.50 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Multiple recent studies have shown that speaker recognition performance using frame-based cepstral features is improved by adding higher-level information, including prosodic and lexical features. This paper explores the important question of finding a good kernel for a system that models syllable-based prosodic features using support vector machines (SVMs). The system has been the best performing of our high-level systems in the last two NIST evaluations, and gives significant improvements when combined with cepstral-based systems. We introduce two new methods for transforming the syllable-level features into a single high-dimensional vector that can be well modeled by SVMs, resulting in significant gains in speaker recognition performance
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on; 05/2007 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Information from speech recognition can be used in various ways in state-of-the-art speaker recognition systems. This includes the obvious use of recognized words to enable the use of text-dependent speaker modeling techniques when the words spoken are not given. Furthermore, it has been shown that the choice of words and phones itself can be a useful indicator of speaker identity. Also, recognizer output enables higher-level features, in particular those related to prosodic properties of speech. Finally, we discuss the use of mere by-products of word recognition, such as subword unit alignments, pronunciations, and speaker adaptation transforms to derive powerful nonstandard features for speaker modeling. We present specific techniques and results from SRI's NIST speaker recognition evaluation system.
Signal Processing Applications for Public Security and Forensics, 2007. SAFE '07. IEEE Workshop on; 05/2007
-
[show abstract]
[hide abstract]
ABSTRACT: We previously proposed the use of MLLR transforms derived from a speech recognition system as speaker features in a speaker verification system. In this paper we report recent improvements to this approach. First, we noticed a fundamental problem in our previous implementation that stemmed from a mismatch between male and female recognition models, and the model transforms they produce. Although it affects only a small percentage of verification trials (those in which the gender detector commits errors), this mismatch has a large effect on average system performance. We solve this problem by consistently using only one recognition model (either male or female) in computing speaker adaptation transforms regardless of estimated speaker gender. A further accuracy boost is obtained by combining feature vectors derived from male and female vectors into one larger feature vector. Using 1-conversation-side training, the final system has about 27% lower decision cost than a state-of-the-art ccpstral GMM speaker system, and 53% lower decision cost when trained on 8 conversation sides per speaker
Speaker and Language Recognition Workshop, 2006. IEEE Odyssey 2006: The; 07/2006
-
[show abstract]
[hide abstract]
ABSTRACT: Recent work in speaker recognition has demonstrated the advantage of modeling stylistic features in addition to traditional cepstral features, but to date there has been little study of the relative contributions of these different feature types to a state-of-the-art system. In this paper we provide such an analysis, based on SRI's submission to the NIST 2005 speaker recognition evaluation. The system consists of 7 subsystems (3 cepstral 4 stylistic). By running independent N-way subsystem combinations for increasing values of N, we fines that (1) a monotonic pattern in the choice of the best N systems allows for the inference of subsystem importance; (2) the ordering of subsystems alternates between cepstral and stylistic; (3) syllable-based prosodic features are the strongest stylistic features, and (4) overall subsystem ordering depends crucially on the amount of training data (1 versus 8 conversation sides). Improvements over the baseline cepstral system, when all systems are combined, range from 47% to 67%, with larger improvements for the 8-side condition. These results provide direct evidence of the complementary contributions of cepstral and stylistic features to speaker discrimination
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on; 06/2006 · 4.63 Impact Factor
-
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on; 02/2005
-
[show abstract]
[hide abstract]
ABSTRACT: In previous work we showed that state-of-the-art end-of-utterance detection (as used, for example, in dialog systems) can be improved significantly by making use of prosodic and/or language models that predict utterance endpoints, based on word and alignment output from a speech recognizer. However, using a recognizer in endpointing might not be practical in certain applications. We demonstrate that the improvements due to the prosodic knowledge can be realized largely without alignment information, i.e., without requiring a speech recognizer. A prosodic end-of-utterance detector using only speech/nonspeech detection output is still considerably more accurate and has lower latency than a baseline system based on pause-length thresholding.
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on; 05/2003 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this work, different prosodic knowledge sources are integrated into a state-of-the-art large vocabulary speech recognition system. Prosody manifests itself on different levels in the speech signal: within the words as a change in phone durations and pitch, in between the words as a variation in the pause length, and beyond the words, correlating with higher linguistic structures and nonlexical phenomena. We investigate three models, each exploiting a different level of prosodic information, in rescoring N-best hypotheses according to how well recognized words correspond to prosodic features of the utterance. Experiments on the Switchboard corpus show word accuracy improvements with each prosodic knowledge source. A further improvement is observed with the combination of all models, demonstrating that they each capture somewhat different prosodic characteristics of the speech signal.
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on; 05/2003 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Dialog act tagging is an important step toward speech understanding, yet training such taggers usually requires large amounts of data labeled by linguistic experts. Here we investigate the use of unlabeled data for training HMM-based dialog act taggers. Three techniques are shown to be effective for bootstrapping a tagger from very small amounts of labeled data: iterative relabeling and retraining on unlabeled data; a dialog grammar to model dialog act context, and a model of the prosodic correlates of dialog acts. On the SPINE dialog corpus, the combined use of prosodic information and unlabeled data reduces the tagging error between 12% and 16%, compared to baseline systems using word information and various amounts of labeled data only.
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on; 05/2003 · 4.63 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Conventional speaker recognition systems identify speakers by using spectral information from very short slices of speech. Such systems perform well (especially in quiet conditions), but fail to capture idiosyncratic longer-term patterns in a speaker's habitual speaking style, including duration and pausing patterns, intonation contours, and the use of particular phrases. We investigate the contribution of modeling such prosodic and lexical patterns, on performance in the NIST 2003 Speaker Recognition Evaluation extended data task. We report results for: (1) systems based on individual feature types alone; (2) systems in combination with a state-of-the-art frame-based baseline system; (3) an all-system combination. Our results show that certain longer-term stylistic features provide powerful complementary information to both frame-level cepstral features and to each other. Stylistic features thus significantly improve speaker recognition performance over conventional systems, and offer promise for a variety of intelligence and security applications.
Automatic Speech Recognition and Understanding, 2003. ASRU '03. 2003 IEEE Workshop on;
-
[show abstract]
[hide abstract]
ABSTRACT: We describe a novel approach to modeling idiosyncratic prosodic behavior for automatic speaker recognition. The approach computes various duration, pitch, and energy features for each estimated syllable in speech recognition output, quantizes the features, forms N-grams of the quantized values, and models normalized counts for each feature N-gram using support vector machines (SVMs). We refer to these features as “SNERF-grams” (N-grams of Syllable-based Nonuniform Extraction Region Features). Evaluation of SNERF-gram performance is conducted on two-party spontaneous English conversational telephone data from the Fisher corpus, using one conversation side in both training and testing. Results show that SNERF-grams provide significant performance gains when combined with a state-of-the-art baseline system, as well as with two highly successful long-range feature systems that capture word usage and lexically constrained duration patterns. Further experiments examine the relative contributions of features by quantization resolution, N-gram length, and feature type. Results show that the optimal number of bins depends on both feature type and N-gram length, but is roughly in the range of 5–10 bins. We find that longer N-grams are better than shorter ones, and that pitch features are most useful, followed by duration and energy features. The most important pitch features are those capturing pitch level, whereas the most important energy features reflect patterns of rising and falling. For duration features, nucleus duration is more important for speaker recognition than are durations from the onset or coda of a syllable. Overall, we find that SVM modeling of prosodic feature sequences yields valuable information for automatic speaker recognition. It also offers rich new opportunities for exploring how speakers differ from each other in voluntary but habitual ways.
Speech Communication.
