Who Really Spoke When? Finding Speaker Turns and Identities in Broadcast News Audio

Tranter, S.E.

doi:10.1109/icassp.2006.1660195

Cited by 30 publications

(46 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Blocking rules are used to stop rules firing in certain contexts, for example, the sequence "[name] reports " assigns the next speaker to be [name] unless is the word "that." An extension of this system described in [47], learns many rules and their associated probability of being correct automatically from the training data and then applies these simultaneously on the test data using probabilistic combination. Using automatic transcriptions and automatically found speaker turns naturally degrades performance but potentially 85% of the time can be correctly assigned to the true speaker identity using this method.…”

Section: H Finding Identitiesmentioning

confidence: 99%

An overview of automatic speaker diarization systems

Tranter

Reynolds

2006

IEEE Trans. Audio Speech Lang. Process.

Self Cite

510

300

View full text Add to dashboard Cite

Abstract-Audio diarization is the process of annotating an input audio channel with information that attributes (possibly overlapping) temporal regions of signal energy to their specific sources. These sources can include particular speakers, music, background noise sources, and other signal source/channel characteristics. Diarization can be used for helping speech recognition, facilitating the searching and indexing of audio archives, and increasing the richness of automatic transcriptions, making them more readable. In this paper, we provide an overview of the approaches currently used in a key area of audio diarization, namely speaker diarization, and discuss their relative merits and limitations. Performances using the different techniques are compared within the framework of the speaker diarization task in the DARPA EARS Rich Transcription evaluations. We also look at how the techniques are being introduced into real broadcast news systems and their portability to other domains and tasks such as meetings and speaker verification.

show abstract

Section: H Finding Identitiesmentioning

confidence: 99%

An overview of automatic speaker diarization systems

Tranter

Reynolds

2006

IEEE Trans. Audio Speech Lang. Process.

Self Cite

510

300

View full text Add to dashboard Cite

show abstract

“…Note that a parallel approach for lexical SID in TV shows is to use lexical context around spoken names to classify the names between speaker, addressee and object [8,29,24]. On the contrary, this work does not depend on spoken names (hence neither on a Named Entity Recognizer), but rather analyzes the general lexical content of speech.…”

Section: Introductionmentioning

confidence: 99%

Lexical speaker identification in TV shows

Bredin

Hartmann

et al. 2014

Multimed Tools Appl

View full text Add to dashboard Cite

It is possible to use lexical information extracted from speech transcripts for speaker identification (SID), either on its own or to improve the performance of standard cepstral-based SID systems upon fusion. This was established before typically using isolated speech from single speakers (NIST SRE corpora, parliamentary speeches). On the contrary, this work applies lexical approaches for SID on a different type of data. It uses the REPERE corpus consisting of unsegmented multiparty conversations, mostly debates, discussions and Q&A sessions from TV shows. It is hypothesized that people give out clues to their identity when speaking in such settings which this work aims to exploit. The impact on SID performance of the diarization front-end required to pre-process the unsegmented data is also measured.Four lexical SID approaches are studied in this work, including TFIDF, BM25 and LDA-based topic modeling. Results are analysed in terms of TV shows and speaker roles. Lexical approaches achieve low error rates for certain speaker roles such as anchors and journalists, sometimes lower than a standard cepstral-based Gaussian Supervector -Support Vector Machine (GSV-SVM) system. Also, in certain cases, the lexical system shows modest improvement over the cepstral-based system performance using score-level sum fusion.To highlight the potential of using lexical information not just to improve upon cepstral-based SID systems but as an independent approach in its own right, initial studies on crossmedia SID is briefly reported. Instead of using speech data as all cepstral systems require, this approach uses Wikipedia texts to train lexical speaker models which are then tested on speech transcripts to identify speakers.

show abstract

“…The use of biometric models for speaker identification appears in [5,14]. However, these audio-only approaches did not achieve good performance because of high errors rates, caused by poor speech transcriptions and bad named-entity detections.…”

Section: Introductionmentioning

confidence: 99%

Tag Propagation Approaches within Speaking Face Graphs for Multimodal Person Discovery

Fonseca

Freire

Patrocínio

et al. 2017

Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

The indexing of broadcast TV archives is a current problem in multimedia research. As the size of these databases grows continuously, meaningful features are needed to describe and connect their elements efficiently, such as the identification of speaking faces. In this context, this paper focuses on two approaches for unsupervised person discovery. Initial tagging of speaking faces is provided by an OCR-based method, and these tags propagate through a graph model based on audiovisual relations between speaking faces. Two propagation methods are proposed, one based on random walks and the other based on a hierarchical approach. To better evaluate their performances, these methods were compared with two graph clustering baselines. We also study the impact of different modality fusions on the graph-based tag propagation scenario. From a quantitative analysis, we observed that the graph propagation techniques always outperform the baselines. Among all compared strategies, the methods based on hierarchical propagation with late fusion and random walk with score-fusion obtained the highest MAP values. Finally, even though these two methods produce highly equivalent results according to Kappa coefficient, the random walk method performs better according to a paired t-test, and the computing time for the hierarchical propagation is more than 4 times lower than the one for the random walk propagation.

show abstract

Who Really Spoke When? Finding Speaker Turns and Identities in Broadcast News Audio

Cited by 30 publications

References 4 publications

An overview of automatic speaker diarization systems

An overview of automatic speaker diarization systems

Lexical speaker identification in TV shows

Tag Propagation Approaches within Speaking Face Graphs for Multimodal Person Discovery

Contact Info

Product

Resources

About