| Title: | Context-dependent factored language models |
|---|
| Authors: | ID Donaj, Gregor (Author)
ID Kačič, Zdravko (Author) |
|---|
| Files: |  EURASIP_Journal_on_Audio,_Speech,_and_Music_Processing_2017_Donaj,_Kacic_Context-dependent_factored_language_models.pdf (1,17 MB)
MD5: 9BFE3D3D19A9B226FC07011D79E111C4
 http://asmp.eurasipjournals.springeropen.com/articles/10.1186/s13636-017-0104-6
|
|---|
| Language: | English |
|---|
| Work type: | Scientific work |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | The incorporation of grammatical information into speech recognition systems is often used to increase performance in morphologically rich languages. However, this introduces demands for sufficiently large training corpora and proper methods of using the additional information. In this paper, we present a method for building factored language models that use data obtained by morphosyntactic tagging. The models use only relevant factors that help to increase performance and ignore data from other factors, thus also reducing the need for large morphosyntactically tagged training corpora. Which data is relevant is determined at run-time, based on the current text segment being estimated, i.e., the context. We show that using a context-dependent model in a two-pass recognition algorithm, the overall speech recognition accuracy in a Broadcast News application improved by 1.73% relatively, while simpler models using the same data achieved only 0.07% improvement. We also present a more detailed error analysis based on lexical features, comparing first-pass and second-pass results. |
|---|
| Keywords: | speech recognition, factored language model, dynamic backoff path, word context, inflectional language, morphosyntactic tags |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Year of publishing: | 2017 |
|---|
| Number of pages: | str. 1-16 |
|---|
| Numbering: | Letn. 2017 |
|---|
| PID: | 20.500.12556/DKUM-66442  |
|---|
| ISSN: | 1687-4722 |
|---|
| UDC: | 004.934 |
|---|
| ISSN on article: | 1687-4722 |
|---|
| COBISS.SI-ID: | 20330774 |
|---|
| DOI: | 10.1186/s13636-017-0104-6 |
|---|
| NUK URN: | URN:SI:UM:DK:CKPFRA1L |
|---|
| Publication date in DKUM: | 26.06.2017 |
|---|
| Views: | 2038 |
|---|
| Downloads: | 388 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
