2010-11 | Semester 1 |
12.10.10 | Review of Interspeech 2010 & planning meeting |
19.10.10 | Recent work in speaker adaption using a VTLN prior Breslin et al (see also Junichi's paper on CSMAPLR for TTS) |
26.10.10 | Spoken term discovery Jansen at al (Fergus) |
02.11.10 | Introduction to WFST decoders Mohri et al. (Arnab) |
09.11.10 | WFST Application to ASR and Direct_Construction_of_Compact_Context-Dependency_Transducers_From_Data.pdf (Ravi) |
16.11.10 | Compressive sensing/sparsity 1 is2010_SRs.pdf , for more, see IBM_SPIF.pdf (Liang) |
23.11.10 | Sparsity 2 IS10_incorporating.pdf, ref.IS10_Modeling.pdf (Liang) |
30.11.10 |
Voice activity detection (Erich)
- reference sohn_SPL99_statistical_model-based_VAD.pdf - main paper ghaemmaghami_IS2010_noise_robust_VAD_td-autocorr.pdf - corpus (optional) dean_IS2010_noise_corpus_VAD.pdf Presentation Listen_Nov10_IS_VAD.pdf |
07.12.10 | No meeting |
14.12.10 | TF-IDF acoustic models (Steve) |
I | Attachment | Action | Size | Date | Who | Comment![]() |
---|---|---|---|---|---|---|
![]() |
Direct_Construction_of_Compact_Context-Dependency_Transducers_From_Data.pdf | manage | 121.6 K | 05 Nov 2010 - 10:42 | RavichanderVipperla | |
![]() |
breslin_adaptation.pdf | manage | 154.6 K | 13 Oct 2010 - 10:56 | Main.s0566164 | |
![]() |
jansen_std.pdf | manage | 323.4 K | 13 Oct 2010 - 11:35 | Main.s0566164 | |
![]() |
yamagishi_csmaplr.pdf | manage | 2411.5 K | 18 Oct 2010 - 12:40 | Main.s0566164 | |
![]() |
dean_IS2010_noise_corpus_VAD.pdf | manage | 123.5 K | 26 Nov 2010 - 11:51 | ErichZwyssig | Dean et al. |
![]() |
ghaemmaghami_IS2010_noise_robust_VAD_td-autocorr.pdf | manage | 179.4 K | 26 Nov 2010 - 11:50 | ErichZwyssig | Ghaemmaghami et al. |
![]() |
IBM_SPIF.pdf | manage | 121.3 K | 11 Nov 2010 - 12:53 | Main.llu | IBM_SPIF Tech. Rep. |
![]() |
IS10_incorporating.pdf | manage | 161.0 K | 18 Nov 2010 - 10:11 | Main.llu | incorporating SPIF in ASR |
![]() |
IS10_incorporatingpdf | manage | 161.0 K | 18 Nov 2010 - 10:08 | Main.llu | incorporating SPIF in ASR |
![]() |
IS10_Modeling.pdf | manage | 243.1 K | 18 Nov 2010 - 10:09 | Main.llu | modeling posterior probabilities using the linear exponential family |
![]() |
mohri-wfst_asr.pdf | manage | 322.7 K | 25 Oct 2010 - 11:01 | Main.v1aghosh | Mohri, Pereira, Riley, "Speech recognition with weighted finite-state transducers", in Springer Handbook on Speech Processing and Speech Communication |
![]() |
Listen_Nov10_IS_VAD.pdf | manage | 767.3 K | 02 Dec 2010 - 11:46 | ErichZwyssig | Slides |
![]() |
sohn_SPL99_statistical_model-based_VAD.pdf | manage | 101.7 K | 26 Nov 2010 - 11:50 | ErichZwyssig | Sohn et al. |
![]() |
is2010_SRs.pdf | manage | 138.0 K | 11 Nov 2010 - 12:47 | Main.llu | sparse representation feature for speech recognition |
![]() |
tfidf_am.pdf | manage | 63.8 K | 06 Dec 2010 - 12:29 | Main.s0566164 | TF-IDF acoustic models |