| Presentation | 2001/12/13 Improvement of N-gram Language Models Using Accent Phrase Boundaries Makoto TERAO, Nobuaki MINEMATSU, Keikichi HIROSE, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Current continuous speech recognition systems make much use of segmental features but little use of prosodic features. This paper proposes a novel method to integrate prosodic boundary information into N-gram-based language modeling. In this method, two types of language sub-models are built. One characterizes word transitions crossing accent phrase boundaries and the other not crossing the boundaries. To realize these two sub-models directly from a speech corpus, its size should be comparable to a text corpus used for N-gram model training. However, the preparation of such a large speech corpus is not realistic. To solve this problem, we focus upon transition of words in terms of their part-of-speech (POS), and differences in POS transition crossing and not crossing the boundaries are used to generate the two sub-models. Through experiments, the proposed model showed 11% perplexity reduction given the correct boundary position, and 8% reduction with the automatically extracted boundaries. Even when test speech samples were spoken by another speaker than the speaker used in characterizing the POS transitions, 6% reduction was observed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | language model / prosody / accent phrase boundary / transition of part-of-speech / continuous speech recognition |
| Paper # | NLC2001-66,SP2001-101 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2001/12/13(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improvement of N-gram Language Models Using Accent Phrase Boundaries |
| Sub Title (in English) | |
| Keyword(1) | language model |
| Keyword(2) | prosody |
| Keyword(3) | accent phrase boundary |
| Keyword(4) | transition of part-of-speech |
| Keyword(5) | continuous speech recognition |
| 1st Author's Name | Makoto TERAO |
| 1st Author's Affiliation | Graduate School of Engineering, University of Tokyo() |
| 2nd Author's Name | Nobuaki MINEMATSU |
| 2nd Author's Affiliation | Graduate School of Information Science and Technology, University of Tokyo |
| 3rd Author's Name | Keikichi HIROSE |
| 3rd Author's Affiliation | Graduate School of Frontier Sciences, University of Tokyo |
| Date | 2001/12/13 |
| Paper # | NLC2001-66,SP2001-101 |
| Volume (vol) | vol.101 |
| Number (no) | 520 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |