Speaker Diarization: About whom the Speaker is Talking ?

Mauclair, Julie; Meignier, Sylvain; Estève, Yannick

doi:10.1109/odyssey.2006.248114

Cited by 19 publications

(26 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our system to identify speakers by name is based on the use of SCT and it is presented in [5] and [7]. A SCT is used for each occurrence of full name detected in the transcripts.…”

Section: Baseline Systemmentioning

confidence: 99%

“…In all the previous papers dealing with named speaker identification, the results were presented in terms of duration [4,5,6,7,8]. That is to say that if a system is able to correctly name a speaker who speaks 90% of the time and miss the other six speakers who speak 10% of the time, it will have very good results (90% of recall and 90% of precision).…”

Section: Scoringmentioning

confidence: 99%

“…A first system, using manual rules [4], was proposed in 2005. In 2006, we have proposed an automatic approach exploiting ASR transcriptions and the outputs of a diarization system [5]. This approach is based on the use of semantic classification trees (SCT).…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we present improvements concerning the SCT-based method [5,7]. In this approach, decisions are taken at two levels: at the segment level (local decisions), and at the audio file one (global decisions).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic named identification of speakers using diarization and ASR systems

Jousse¹,

Petitrenaud²,

Meignier³

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

In this paper, we consider the extraction of speaker identity from audio records of broadcast news without a priori acoustic information about speakers. Using an automatic speech recognition system and an automatic speaker diarization system, we present improvements for a method which allows to extract speaker identities from automatic transcripts and to assign them to speech segments.Experiments are carried out on French broadcast news records from the ESTER 1 evaluation campaign. Experimental results using outputs of automatic speech recognition and automatic diarization are presented.

show abstract

“…Our system to identify speakers by name is based on the use of SCT and it is presented in [5] and [7]. A SCT is used for each occurrence of full name detected in the transcripts.…”

Section: Baseline Systemmentioning

confidence: 99%

Section: Scoringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic named identification of speakers using diarization and ASR systems

Jousse¹,

Petitrenaud²,

Meignier³

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

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