Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-L11.4 |
| Session: | Language Modeling and Search |
| Time: | Friday, May 21, 16:30 - 16:50 |
| Presentation: |
Lecture |
| Topic: |
Speech Processing: Large Vocabulary Recognition/Search |
| Title: |
VOCABULARY-INDEPENDENT SEARCH IN SPONTANEOUS SPEECH |
| Authors: |
Frank Seide; Microsoft Research Asia | | |
| | Peng Yu; Microsoft Research Asia | | |
| | Chengyuan Ma; Microsoft Research Asia | | |
| | Eric Chang; Microsoft Research Asia | | |
| Abstract: |
For efficient organization of speech recordings - meetings, interviews, voice mails, lectures - the ability to search for spoken keywords is an essential capability. Today, most spoken-document retrieval systems use large-vocabulary recognition. For the above scenarios, such systems suffer from both the unpredictable vocabulary/domain and generally high word-error rates (WER).In this paper, we present a vocabulary-independent system to index and rapidly search spontaneous speech. A speech recognizer generates lattices of phonetic word fragments, against which keywords are matched phonetically.We will first show the need to use recognition alternatives (lattices) in a high-WER context, on a word-based baseline. Then we will introduce our new method of phonetic word-fragment lattice generation, which uses longer-span language knowledge than a phoneme recognizer. Last we will introduce heuristics to compact the lattices to feasible sizes that can be searched efficiently.On the LDC Voicemail corpus, we show that vocabulary/domain-independent phonetic search is as accurate as a vocabulary/domain-dependent word-lattice based baseline system for in-vocabulary keywords (FOMs of 74-75%), but nearly maintains this accuracy also for OOV keywords. |
| |
| Back | |