COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > CUED Speech Group Seminars > Robust speech recognition / Towards better probabilistic models of speech - a discussion
Robust speech recognition / Towards better probabilistic models of speech - a discussionAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Catherine Breslin. BRIDGING THE GAP BETWEEN SPEECH ENHANCEMENT AND RECOGNITION , Takuya Yoshioka One major goal of ASR is to accurately transcribe target utterances even in acoustically adverse environments and this has been tackled with a range of approaches. The approaches to noise robust ASR systems can be broadly classified into two categories. One is based on speech enhancement, which attempts to clean speech signals that are corrupted by noise. The speech enhancement approaches are usually optimized using SNR or related critetia. The approaches in the other category, including feature/model-space VTS , JUD, and SPLICE , are more tailored to ASR in the sense that they exploit statistical models of clean feature vectors for effective compensation for noise. In this short talk, I will argue that these two types of approaches have different advantages and present a novel general scheme for integrating them. I will also present applications of this scheme to meeting transcription and reverberant speech recognition. I try to explain the basic concept without using too many equations so that the talk would be enjoyable for everyone in this group. TOWARDS BETTER PROBABILISTIC MODELS OF SPEECH : WHY SAMPLED TRAJECTORIES SOUND BAD AND HOW TO FIX THEM - A DISCUSSION , Matt Shannon Matt will present some preliminary experimental results and some thought provoking speech samples for discussion. This talk is part of the CUED Speech Group Seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsIII Pint of Knowledge Liberia's Independence Day Talk General talks Seminars at the Department of Biochemistry Language Acquisition and Processing Research Cluster Engineering - Mechanics, Materials and Design (Div C) - talks and eventsOther talksmTORC1 signaling coordinates different POMC neurons subpopulations to regulate feeding Access to Medicines White dwarfs as tracers of cosmic, galactic, stellar & planetary evolution Fukushima and the law Ethics for the working mathematician, seminar 9 CANCELLED Surrogate models in Bayesian Inverse Problems Active bacterial suspensions: from individual effort to team work DataFlow SuperComputing for BigData Protein Folding, Evolution and Interactions Symposium Sneks long balus Simulating Electricity Prices: negative prices and auto-correlation |