Publications

Refine Results

(Filters Applied) Clear All

Bridging the gap between linguists and technology developers: large-scale, sociolinguistic annotation for dialect and speaker recognition

May 28, 2008
  |
Conference Paper
Author:
Christopher Cieri
…
Published in:
Proc. 6th Int. Conf. on Language Resources and Evaluation, LREC, 28 May 2008.
Topic:
cyber security
R&D area:
R&D group:

Summary

Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the language recognition community, there is growing interest in differentiating not only languages but also mutually intelligible dialects of a single language. Decades of research in dialectology suggest that high-level features can enable systems to cluster speakers according to the dialects they speak. The Phanotics (Phonetic Annotation of Typicality in Conversational Speech) project seeks to identify high-level features characteristic of American dialects, annotate a corpus for these features, use the data to dialect recognition systems and also use the categorization to create better models for speaker recognition. The data, once published, should be useful to other developers of speaker and dialect recognition systems and to dialectologists and sociolinguists. We expect the methods will generalize well beyond the speakers, dialects, and languages discussed here and should, if successful, provide a model for how linguists and technology developers can collaborate in the future for the benefit of both groups and toward a deeper understanding of how languages vary and change.
READ LESS

Summary

Recent years have seen increased interest within the speaker recognition community in high-level features including, for example, lexical choice, idiomatic expressions or syntactic structures. The promise of speaker recognition in forensic applications drives development toward systems robust to channel differences by selecting features inherently robust to channel difference. Within the...

READ MORE
Bridging the gap between linguists and technology developers: large-scale, sociolinguistic annotation for dialect and speaker recognition

Retrieval and browsing of spoken content

May 1, 2008
  |
Journal Article
Author:
Ciprian Chelba
…
Published in:
IEEE Signal Process. Mag., Vol. 25, No. 3, May 2008, pp. 39-49.
Topic:
speech recognition
R&D area:
R&D group:

Summary

Ever-increasing computing power and connectivity bandwidth, together with falling storage costs, are resulting in an overwhelming amount of data of various types being produced, exchanged, and stored. Consequently, information search and retrieval has emerged as a key application area. Text-based search is the most active area, with applications that range from Web and local network search to searching for personal information residing on one's own hard-drive. Speech search has received less attention perhaps because large collections of spoken material have previously not been available. However, with cheaper storage and increased broadband access, there has been a subsequent increase in the availability of online spoken audio content such as news broadcasts, podcasts, and academic lectures. A variety of personal and commercial uses also exist. As data availability increases, the lack of adequate technology for processing spoken documents becomes the limiting factor to large-scale access to spoken content. In this article, we strive to discuss the technical issues involved in the development of information retrieval systems for spoken audio documents, concentrating on the issue of handling the errorful or incomplete output provided by ASR systems. We focus on the usage case where a user enters search terms into a search engine and is returned a collection of spoken document hits.
READ LESS

Summary

Ever-increasing computing power and connectivity bandwidth, together with falling storage costs, are resulting in an overwhelming amount of data of various types being produced, exchanged, and stored. Consequently, information search and retrieval has emerged as a key application area. Text-based search is the most active area, with applications that range...

READ MORE
Retrieval and browsing of spoken content

Adaptive short-time analysis-synthesis for speech enhancement

March 31, 2008
  |
Conference Paper
Author:
Prabahan Basu
…
Published in:
2008 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, 31 March - 4 April 2008.
Topic:
speech enhancement
R&D area:
R&D group:

Summary

In this paper we propose a multiresolution short-time analysis method for speech enhancement. It is well known that fixed resolution methods such as the traditional short-time Fourier transform do not generally match the time-frequency structure of the signal being analyzed resulting in poor estimates of the speech and noise spectra required for enhancement. This can lead to the reduction of quality in the enhanced signal through the introduction of artifacts such as musical noise. To counter these limitations, we propose an adaptive short-time analysis-synthesis scheme for speech enhancement in which the adaptation is based on a measure of local time-frequency concentration. Synthesis is made possible through a modified overlap-add procedure. Empirical results using voiced speech indicate a clear improvement over a fixed time-frequency resolution enhancement scheme both in terms of mean-square error and as indicated by informal listening tests.
READ LESS

Summary

In this paper we propose a multiresolution short-time analysis method for speech enhancement. It is well known that fixed resolution methods such as the traditional short-time Fourier transform do not generally match the time-frequency structure of the signal being analyzed resulting in poor estimates of the speech and noise spectra...

READ MORE
Adaptive short-time analysis-synthesis for speech enhancement

A covariance kernel for SVM language recognition

March 31, 2008
  |
Conference Paper
Author:
William M. Campbell
Published in:
ICASSP 2008, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 31 March - 4 April 2008, pp. 4141-4144.
Topic:
language recognition
R&D area:
R&D group:

Summary

Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has proven effective. A recent successful example of this paradigm is SVM-based discrimination of languages based on GMM mean supervectors (GSVs). GSVs are created through MAP adaptation of a universal background model (UBM) GMM. This work proposes a novel extension to this idea by extending the supervector framework to the covariances of the UBM. We demonstrate a new SVM kernel including this covariance structure. In addition, we propose a method for pushing SVM model parameters back to GMM models. These GMM models can be used as an alternate form of scoring. The new approach is demonstrated on a fourteen language task with substantial performance improvements over prior techniques.
READ LESS

Summary

Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has proven effective. A recent successful example of this paradigm is SVM-based discrimination of languages based on GMM mean supervectors (GSVs). GSVs are created through MAP adaptation of...

READ MORE
A covariance kernel for SVM language recognition

A multi-class MLLR kernel for SVM speaker recognition

March 31, 2008
  |
Conference Paper
Author:
Zahi N. Karam
…
Published in:
Proc. IEEE Int. Connf. on Acoustics, Speech and Signal Processing, ICASSP, 31 March - 4 April 2008, pp. 4117-4120.
Topic:
speaker recognition
R&D area:
R&D group:

Summary

Speaker recognition using support vector machines (SVMs) with features derived from generative models has been shown to perform well. Typically, a universal background model (UBM) is adapted to each utterance yielding a set of features that are used in an SVM. We consider the case where the UBM is a Gaussian mixture model (GMM), and maximum likelihood linear regression (MLLR) adaptation is used to adapt the means of the UBM. Recent work has examined this setup for the case where a global MLLR transform is applied to all the mixture components of the GMM UBM. This work produced positive results that warrant examining this setup with multi-class MLLR adaptation, which groups the UBM mixture components into classes and applies a different transform to each class. This paper extends the MLLR/GMM framework to the multiclass case. Experiments on the NIST SRE 2006 corpus show that multi-class MLLR improves on global MLLR and that the proposed system?s performance is comparable with state of the art systems.
READ LESS

Summary

Speaker recognition using support vector machines (SVMs) with features derived from generative models has been shown to perform well. Typically, a universal background model (UBM) is adapted to each utterance yielding a set of features that are used in an SVM. We consider the case where the UBM is a...

READ MORE
A multi-class MLLR kernel for SVM speaker recognition

Exploiting temporal change in pitch in formant estimation

March 31, 2008
  |
Conference Paper
Author:
Tianyu Tom Wang
…
Published in:
Proc. IEEE Int. Conf. on Acoustic, Speech, and Signal Processes, ICASSP, 31 March - 4 April 2008, pp. 3929-3932.
Topic:
signal processing
R&D area:
R&D group:

Summary

This paper considers the problem of obtaining an accurate spectral representation of speech formant structure when the voicing source exhibits a high fundamental frequency. Our work is inspired by auditory perception and physiological modeling studies implicating the use of temporal changes in speech by humans. Specifically, we develop and assess signal processing schemes aimed at exploiting temporal change of pitch as a basis for formant estimation. Our methods are cast in a generalized framework of two-dimensional processing of speech and show quantitative improvements under certain conditions over representations derived from traditional and homomorphic linear prediction. We conclude by highlighting potential benefits of our framework in the particular application of speaker recognition with preliminary results indicating a performance gender-gap closure on subsets of the TIMIT corpus.
READ LESS

Summary

This paper considers the problem of obtaining an accurate spectral representation of speech formant structure when the voicing source exhibits a high fundamental frequency. Our work is inspired by auditory perception and physiological modeling studies implicating the use of temporal changes in speech by humans. Specifically, we develop and assess...

READ MORE
Exploiting temporal change in pitch in formant estimation

Language recognition with discriminative keyword selection

March 31, 2008
  |
Conference Paper
Author:
Frederick S. Richardson
…
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, 31 March - 4 April 2008, pp. 4145-4148.
Topic:
language recognition
R&D area:
R&D group:

Summary

One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to determine the target language. The language classification is typically performed by extracting N-gram statistics from the token sequences and then using an N-gram language model or support vector machine (SVM) to perform the classification. One problem with these approaches is that the number of N-grams grows exponentially as the order N is increased. This is especially problematic for an SVM classifier as each utterance is represented as a distinct N-gram vector. In this paper we propose a novel approach for modeling higher order Ngrams using an SVM via an alternating filter-wrapper feature selection method. We demonstrate the effectiveness of this technique on the NIST 2007 language recognition task.
READ LESS

Summary

One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to determine the target language. The language classification is typically performed by extracting N-gram statistics from the token sequences and...

READ MORE
Language recognition with discriminative keyword selection

Multisensor very low bit rate speech coding using segment quantization

March 31, 2008
  |
Conference Paper
Author:
Alan V. McCree
…
Published in:
Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP, 31 March - 4 April 2008, pp. 3997-4000.
Topic:
speech processing
R&D area:
R&D group:

Summary

We present two approaches to noise robust very low bit rate speech coding using wideband MELP analysis/synthesis. Both methods exploit multiple acoustic and non-acoustic input sensors, using our previously-presented dynamic waveform fusion algorithm to simultaneously perform waveform fusion, noise suppression, and crosschannel noise cancellation. One coder uses a 600 bps scalable phonetic vocoder, with a phonetic speech recognizer followed by joint predictive vector quantization of the error in wideband MELP parameters. The second coder operates at 300 bps with fixed 80 ms segments, using novel variable-rate multistage matrix quantization techniques. Formal test results show that both coders achieve equivalent intelligibility to the 2.4 kbps NATO standard MELPe coder in harsh acoustic noise environments, at much lower bit rates, with only modest quality loss.
READ LESS

Summary

We present two approaches to noise robust very low bit rate speech coding using wideband MELP analysis/synthesis. Both methods exploit multiple acoustic and non-acoustic input sensors, using our previously-presented dynamic waveform fusion algorithm to simultaneously perform waveform fusion, noise suppression, and crosschannel noise cancellation. One coder uses a 600 bps...

READ MORE
Multisensor very low bit rate speech coding using segment quantization

Improved GMM-based language recognition using constrained MLLR transforms

March 30, 2008
  |
Conference Paper
Author:
Wade Shen
…
Published in:
Proc. 33rd IEEE Int. Conf. on Acoustics, Speech, and SIgnal Processing, ICASSP, 30 March - 4 April 2008, pp. 4149-4152.
Topic:
language recognition
R&D area:
R&D group:

Summary

In this paper we describe the application of a feature-space transform based on constrained maximum likelihood linear regression for unsupervised compensation of channel and speaker variability to the language recognition problem. We show that use of such transforms can improve baseline GMM-based language recognition performance on the 2005 NIST Language Recognition Evaluation (LRE05) task by 38%. Furthermore, gains from CMLLR are additive with other modeling enhancements such as vocal tract length normalization (VTLN). Further improvement is obtained using discriminative training, and it is shown that a system using only CMLLR adaption produces state-of-the-art accuracy with decreased test-time computational cost than systems using VTLN.
READ LESS

Summary

In this paper we describe the application of a feature-space transform based on constrained maximum likelihood linear regression for unsupervised compensation of channel and speaker variability to the language recognition problem. We show that use of such transforms can improve baseline GMM-based language recognition performance on the 2005 NIST Language...

READ MORE
Improved GMM-based language recognition using constrained MLLR transforms

Analytic theory of power law graphs

March 12, 2008
  |
Abstract
Author:
Jeremy Kepner
Published in:
SIAM Conference on Parallel Processing for Scientific Computing
Topic:
graph processing
R&D area:
R&D group:

Summary

An analytical theory of power law graphs is presented basedon the Kronecker graph generation technique. The analysisuses Kronecker exponentials of complete bipartite graphsto formulate the sub-structure of such graphs. This allows various high level quantities (e.g. degree distribution,betweenness centrality, diameter, eigenvalues, and isoparametric ratio) to be computed directly from the model pa-rameters. The implications of this work on “clustering”and “dendragram” heuristics are also discussed.
READ LESS

Summary

An analytical theory of power law graphs is presented basedon the Kronecker graph generation technique. The analysisuses Kronecker exponentials of complete bipartite graphsto formulate the sub-structure of such graphs. This allows various high level quantities (e.g. degree distribution,betweenness centrality, diameter, eigenvalues, and isoparametric ratio) to be computed directly from the...

READ MORE
Analytic theory of power law graphs
491-500 of 809