Exploiting Chinese character models to improve speech recognition performance

The Chinese language is based on characters which are syllabic in nature. Since languages have syllabotactic rules which govern the construction of syllables and their allowed sequences, Chinese character sequence models can be used as a first level approximation of allowed syllable sequences. N-gram character sequence models were trained on 4.3 billion characters. Characters are used as a first level recognition unit with multiple pronunciations per character. For comparison the CU-HTK Mandarin word based system was used to recognize words which were then converted to character sequences. The character only system error rates for one best recognition were slightly worse than word based character recognition. However combining the two systems using log-linear combination gives better results than either system separately. An equally weighted combination gave consistent CER gains of 0.1-0.2% absolute over the word based standard system. Copyright © 2009 ISCA.

Syllable language models for Mandarin speech recognition: exploiting character language models.

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

On the generality of crowding: visual crowding in size, saturation, and hue compared to orientation.

Perception of peripherally viewed shapes is impaired when surrounded by similar shapes. This phenomenon is commonly referred to as "crowding". Although studied extensively for perception of characters (mainly letters) and, to a lesser extent, for orientation, little is known about whether and how crowding affects perception of other features. Nevertheless, current crowding models suggest that the effect should be rather general and thus not restricted to letters and orientation. Here, we report on a series of experiments investigating crowding in the following elementary feature dimensions: size, hue, and saturation. Crowding effects in these dimensions were benchmarked against those in the orientation domain. Our primary finding is that all features studied show clear signs of crowding. First, identification thresholds increase with decreasing mask spacing. Second, for all tested features, critical spacing appears to be roughly half the viewing eccentricity and independent of stimulus size, a property previously proposed as the hallmark of crowding. Interestingly, although critical spacings are highly comparable, crowding magnitude differs across features: Size crowding is almost as strong as orientation crowding, whereas the effect is much weaker for saturation and hue. We suggest that future theories and models of crowding should be able to accommodate these differences in crowding effects.