Online Speaker Clustering Using Incremental Learning of an Ergodic Hidden Markov Model

Koshinaka, Takafumi; Nagatomo, Kentaro; Sairyo, Koichi

doi:10.1587/transinf.e95.d.2469

Cited by 6 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm can be seen as an online version of the VBx [27] with simplified prior on assignments p(Z). It is also similar to the algorithm from [7], where the authors modified the offline variational inference to make it suitable for online processing.…”

Section: Model-based Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Back-ends for Online Speaker Recognition and Clustering

Sholokhov¹,

Kuzmin²,

Lee³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario. First, we show that popular cosine scoring suffers from poor score calibration with a varying number of enrollment utterances. Second, we propose a simple replacement for cosine scoring based on an extremely constrained version of probabilistic linear discriminant analysis (PLDA). The proposed model improves over the cosine scoring for multi-enrollment recognition while keeping the same performance in the case of one-to-one comparisons. Finally, we consider an online speaker clustering task where each step naturally involves multi-enrollment recognition. We propose an online clustering algorithm allowing us to take benefits from the PLDA model such as the ability to handle uncertainty and better score calibration. Our experiments demonstrate the effectiveness of the proposed algorithm.

show abstract

Section: Model-based Clusteringmentioning

confidence: 99%

“…Another example is online speaker diarization or clustering [4][5][6][7][8][9]. In this case, short speech segments from an audio stream have to be classified with low latency (e.g.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Back-ends for Online Speaker Recognition and Clustering

Sholokhov¹,

Kuzmin²,

Lee³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A number of online diarization [11,12,13,14,15] and speaker tracking [16,17] solutions have been reported. These use online speaker clustering algorithms [18,19]. Only speaker tracking systems assume prior knowledge of target speakers but they do not consider latency.…”

Section: Prior Workmentioning

confidence: 99%

Low-latency speaker spotting with online diarization and detection

Patino¹,

Yin²,

Delgado³

et al. 2018

The Speaker and Language Recognition Workshop (Odyssey 2018)

View full text Add to dashboard Cite

This paper introduces a new task termed low-latency speaker spotting (LLSS). Related to security and intelligence applications, the task involves the detection, as soon as possible, of known speakers within multi-speaker audio streams. The paper describes differences to the established fields of speaker diarization and automatic speaker verification and proposes a new protocol and metrics to support exploration of LLSS. These can be used together with an existing, publicly available database to assess the performance of LLSS solutions also proposed in the paper. They combine online diarization and speaker detection systems. Diarization systems include a naive, over-segmentation approach and fully-fledged online diarization using segmental i-vectors. Speaker detection is performed using Gaussian mixture models, i-vectors or neural speaker embeddings. Metrics reflect different approaches to characterise latency in addition to detection performance. The relative performance of each solution is dependent on latency. When higher latency is admissible, i-vector solutions perform well; embeddings excel when latency must be kept to a minimum. With a need to improve the reliability of online diarization and detection, the proposed LLSS framework provides a vehicle to fuel future research in both areas. In this respect, we embrace a reproducible research policy; results can be readily reproduced using publicly available resources and open source codes.

show abstract

“…We first considered an approach of using a video recognition technology to summarize a movie. In audio and video recognition technology, there are studies of "speaker clustering" to classify speeches to each speaker [24], and "speaker indexes" to capture "who spoke, and when" [25]. Speaker clustering is a technique that classifies speech utterances from multiple speakers in broadcast news, and meetings, etc.…”

Section: Related Workmentioning

confidence: 99%

Estimation of Interpersonal Relationships in Movies

Ohwatari

Kawamura

Sei

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn many movies, social conditions and awareness of the issues of the times are depicted in any form. Even if fantasy and science fiction are works far from reality, the character relationship does mirror the real world. Therefore, we try to understand social conditions of the real world by analyzing the movie. As a way to analyze the movies, we propose a method of estimating interpersonal relationships of the characters, using a machine learning technique called Markov Logic Network (MLN) from movie script databases on the Web. The MLN is a probabilistic logic network that can describe the relationships between characters, which are not necessarily satisfied on every line. In experiments, we confirmed that our proposed method can estimate favors between the characters in a movie with F-measure of 58.7%. Finally, by comparing the relationships with social indicators, we discussed the relevance of the movies to the real world.

show abstract

Online Speaker Clustering Using Incremental Learning of an Ergodic Hidden Markov Model

Cited by 6 publications

References 11 publications

Probabilistic Back-ends for Online Speaker Recognition and Clustering

Probabilistic Back-ends for Online Speaker Recognition and Clustering

Low-latency speaker spotting with online diarization and detection

Estimation of Interpersonal Relationships in Movies

Contact Info

Product

Resources

About