Modeling out-of-vocabulary words for robust speech recognition

By Issam Bazzi, James R. Glass. 2000

134 citations recorded by the source corpus.

In this paper we present an approach for modeling and recognizing out-of-vocabulary (OOV) words in a single stage recognizer. A word-based recognizer is augmented with an extra OOV word model, which enables the OOV word to be predicted by a word-based language model. The OOV model itself is phone-based, so that an OOV word can be realized as an arbitrary sequence of phones. A phone bigram is used to provide phonotactic constraints within the OOV model. A recognizer with this configuration can recognize words in the original vocabulary as well as any potential new words of arbitrary pronunciation. In our preliminary investigation of this framework, we have evaluated the recognizer on a weather information domain with one test set containing only in-vocabulary (IV) data, and another containing OOV words. On the IV test set, the recognizer had an OOV in-sertion rate of only 1.3%, and degraded the baseline WER from 10.4% to 10.7%. On the OOV test set, the recognizer was able to detect nearly half of the OOV words (47% detection rate).

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dong Yu
2. Li Deng
3. Yoshua Bengio
4. Kyunghyun Cho
5. Graham Neubig
6. Jianfeng Gao
7. Mohit Bansal
8. Quoc V. Le

In Natural Language Processing

1. Rico Sennrich
2. Kyunghyun Cho
3. Li Deng
4. Dong Yu
5. Graham Neubig
6. Barry Haddow
7. Michael Auli
8. Jianfeng Gao

Citations in the corpus

• Neural Machine Translation of Rare Words with Subword Units (2015, methodology): “For speech recognition, phone-level language models have been used (Bazzi and Glass, 2000).”
• WordICA—emergence of linguistic representations for words by independent component analysis (2010, background): “How these out-of-vocabulary words are dealt with is often crucial to the performance of a natural language engineering applications such as speech recognition (Bazzi and Glass 2000).”
• Exploiting deep neural networks for detection-based speech recognition (2013, methodology): “…model, the context-dependent (CD)-DNN-HMM proposed in [33] has been successfully applied to large vocabulary speech recognition tasks and can cut word error rate by up to one third on the challenging conversational speech transcription tasks compared to the discriminatively trained conventional…”
• Automatic alignment and error correction of human generated transcripts for long speech recordings (2006, methodology): “Instead, we assume that errors in the transcript are possible and we allow insertions of new words and substitutions for existing words through the use of a phonetic-based out-of-vocabulary (OOV) word filler model [3].”