Blind Speaker Clustering

Iyer, Ananth N.; Ofoegbu, U.O.; Yantorno, Robert E.; Smolenski, Brett Y.

doi:10.1109/ispacs.2006.364902

Cited by 10 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In telephone conversations, homogeneous speaker utterances are short because speakers change relatively frequently (Iyer et al 2006;Ofoegbu et al 2006a); moreover, information about speaker change points is not usually available. Consequently, increasing the length of data segments used in comparison does not necessarily result in an increase in speaker differentiation performance, as data from more than one speaker could be combined in the same segment.…”

Section: Discussionmentioning

confidence: 99%

“…In this study, the speaker count is assumed to be known as the goal here is to simply compare the clustering performance. Moreover, separate investigations have already been performed to determine the speaker in a given conversation (Ofoegbu et al 2006b(Ofoegbu et al , 2006cIyer et al 2006). Note that the task of speaker clustering is different from SID, due to the fact that telephone conversations are analyzed, where the presence of long speaker homogeneous utterances is limited.…”

Section: Speaker Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Speaker distinguishing distances: a comparative study

Iyer¹,

Ofoegbu²,

Yantorno

et al. 2007

Int J Speech Technol

View full text Add to dashboard Cite

Speaker discrimination is a vital aspect of speaker recognition applications such as speaker identification, verification, clustering, indexing and change-point detection. These tasks are usually performed using distance-based approaches to compare speaker models or features from homogeneous speaker segments in order to determine whether or not they belong to the same speaker. Several distance measures and features have been examined for all the different applications, however, no single distance or feature has been reported to perform optimally for all applications in all conditions. In this paper, a thorough analysis is made to determine the behavior of some frequently used distance measures, as well as features, in distinguishing speakers for different data lengths. Measures studied include the Mahalanobis distance, Kullback-Leibler (KL) distance, T 2 statistic, Hellinger distance, Bhattacharyya distance, Generalized Likelihood Ratio (GLR), Levenne distance, L 2 and L ∞ distances. The Mel-Scale Frequency Cepstral Coefficient (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Line Spectral Pairs (LSP) and the Log Area Ratios (LAR) comprise the features investigated. The usefulness of these measures is studied for different data lengths. Generally, a larger data size for each speaker results in better speaker A.N. Iyer ( ) differentiating capability, as more information can be taken into account. However, in some applications such as segmentation of telephone data, speakers change frequently, making it impossible to obtain large speaker-consistent utterances (especially when speaker change-points are unknown). A metric is defined for determining the probability of speaker discrimination error obtainable for each distance measure using each feature set, and the effect of data size on this probability is observed. Furthermore, simple distancebased speaker identification and clustering systems are developed, and the performances of each distance and feature for various data sizes are evaluated on these systems in order to illustrate the importance of choosing the appropriate distance and feature for each application. Results show that for tasks which do not involve any limitation of data length, such as speaker identification, the Kullback Leibler distance with the MFCCs yield the highest speaker differentiation performance, which is comparable to results obtained using more complex state-of-the-art speaker identification systems. Results also indicate that the Hellinger and Bhattacharyya distances with the LSPs yield the best performance for small data sizes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Speaker Clusteringmentioning

confidence: 99%

Speaker distinguishing distances: a comparative study

Iyer¹,

Ofoegbu²,

Yantorno

et al. 2007

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

“…In contrast, SensePresence's occupancy counting process is entirely unsupervised. The authors of [11] used unsupervised techniques to perform speaker clustering using distances of the feature vectors extracted from different speakers. However this occupant estimation has been done only on telephonic conversational data where our proposed system, SensePresence performs speaker counting without any staged conversational setup.…”

Section: Related Workmentioning

confidence: 99%

SensePresence: Infrastructure-Less Occupancy Detection for Opportunistic Sensing Applications

Khan

Hossain

Roy

2015

2015 16th IEEE International Conference on Mobile Data Management

View full text Add to dashboard Cite

Predicting the occupancy related information in an environment has been investigated to satisfy the myriad requirements of various evolving pervasive, ubiquitous, opportunistic and participatory sensing applications. Infrastructure and ambient sensors based techniques have been leveraged largely to determine the occupancy of an environment incurring a significant deployment and retrofitting costs. In this paper, we advocate an infrastructure-less zero-configuration multimodal smartphone sensor-based techniques to detect fine-grained occupancy information. We propose to exploit opportunistically smartphones' acoustic sensors in presence of human conversation and motion sensors in absence of any conversational data. We develop a novel speaker estimation algorithm based on unsupervised clustering of overlapped and non-overlapped conversational data to determine the number of occupants in a crowded environment. We also design a hybrid approach combining acoustic sensing opportunistically with locomotive model to further improve the occupancy detection accuracy. We evaluate our algorithms in different contexts; conversational, silence and mixed in presence of 10 domestic users. Our experimental results on real-life data traces collected from 10 occupants in natural setting show that using this hybrid approach we can achieve approximately 0.76 error count distance for occupancy detection accuracy on average.

show abstract

“…Owing to the lack of knowledge regarding the real number of speakers, the discussed problem can be interpreted as an unsupervised learning problem. Classic solutions to the problem formulated in this way are based on the concept of hierarchical clustering, where different numbers of groups are checked and various distance measures are used: Mahalanobis distance (Iyer et al, 2006), Bhattacharyya distance (Basseville, 1989), Hellinger distance (Lu et al, 2003), and Generalized Likelihood Ratio (GLR) (Anderson, 2003). Further development of the discussed HC methods has given rise to the clustering algorithm applying Leader Following Concept (LFC) to k-means algorithm (Duda et al, 2001 …”

Section: Introductionmentioning

confidence: 99%

An Effective Speaker Clustering Method using UBM and Ultra-Short Training Utterances

Hossa¹,

Makowski²

2016

Archives of Acoustics

View full text Add to dashboard Cite

The same speech sounds (phones) produced by different speakers can sometimes exhibit significant differences. Therefore, it is essential to use algorithms compensating these differences in ASR systems. Speaker clustering is an attractive solution to the compensation problem, as it does not require long utterances or high computational effort at the recognition stage. The report proposes a clustering method based solely on adaptation of UBM model weights. This solution has turned out to be effective even when using a very short utterance. The obtained improvement of frame recognition quality measured by means of frame error rate is over 5%.It is noteworthy that this improvement concerns all vowels, even though the clustering discussed in this report was based only on the phoneme a. This indicates a strong correlation between the articulation of different vowels, which is probably related to the size of the vocal tract.

show abstract

Blind Speaker Clustering

Cited by 10 publications

References 10 publications

Speaker distinguishing distances: a comparative study

Speaker distinguishing distances: a comparative study

SensePresence: Infrastructure-Less Occupancy Detection for Opportunistic Sensing Applications

An Effective Speaker Clustering Method using UBM and Ultra-Short Training Utterances

Contact Info

Product

Resources

About