| 1 |
Lexical speaker identification in TV shows
|
|
|
|
In: ISSN: 1380-7501 ; EISSN: 1573-7721 ; Multimedia Tools and Applications ; https://hal.archives-ouvertes.fr/hal-01690342 ; Multimedia Tools and Applications, Springer Verlag, 2015, 74 (4), pp.1377 - 1396. ⟨10.1007/s11042-014-1940-3⟩ (2015)
|
|
Abstract:
The final publication is available at https://link.springer.com/article/10.1007/s11042-014-1940-3 ; International audience ; 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 2 Anindya Roy et al. 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.
|
|
Keyword:
[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]; [INFO]Computer Science [cs]
|
|
URL: https://hal.archives-ouvertes.fr/hal-01690342/file/paper_v0.pdf
https://hal.archives-ouvertes.fr/hal-01690342/document
https://doi.org/10.1007/s11042-014-1940-3
https://hal.archives-ouvertes.fr/hal-01690342
|
|
BASE
|
|
Hide details
|
|
|
|
|
