Automatic Methods. Except with respect to Non-ERISA Plans, subject to Section 6.4 below, and unless a Participant (or his or her spouse) elects an optional form of distribution or alternate Beneficiary pursuant to a Qualified Election, distributions from the Account shall be made as follows:
Automatic Methods. No Orthography
5.2.2.1.1 No Orthography, ASR If no orthographic annotation is present, an obvious solution would be to use ASR to obtain it. However, since ASR is not flawless, this orthographic transcription is likely to contain ASR errors. These errors in the orthographic transcription would counterbalance the positive effects of using the orthographic representation for obtaining automatic phonological transcriptions. Whether the net effect is positive depends on the task. For some tasks that are relatively easy for ASR, such as isolated digit recognition, the net effect may even be positive, but for most tasks this will probably not be the case.
5.2.2.1.2 No Orthography, Phone Recognition Another option, if no orthographic representation is available, is to use phone recognition (see section 2.1 on ASR). For this purpose, completely unrestricted phone recognition can be used, but usually some (phonotactic) constraints are employed in the form of a phone language model. Phone accuracy can be highly variable, roughly between 30 and 70 per cent, depending on factors such as speech style and quality of the speech (amount of background noise) (see x.x. Xxxxx 2002). For instance, for one of our ASR systems we measured a phone accuracy level of 63 per cent for extemporaneous speech (Xxxxxx et al. 1998). In general, high accuracy values can be obtained for relatively easy tasks (e.g. carefully read speech), and by carefully tuning the ASR system for specific tasks (i.e. speech style, dialect or accent, gender, or speaker). In general, such levels of phone accuracy are too low, and thus the resulting automatic phonological transcriptions cannot be used directly for most applications. Still, phone recognition can be useful. For our ASR system with a phone accuracy of 63 per cent we examined the resulting phone strings by comparing them to canonical transcriptions (Xxxxxx et al. 1998). Canonical transcriptions can be obtained by means of lexicons, grapheme-to-phoneme conversion tools (for an overview, see Bisani and Ney 2008), or a combination of the two. Since the quality of the phonological transcriptions in lexicons is usually better than that of grapheme-to-phoneme conversion tools, in many applications one first looks up the phonological transcriptions of words in lexicons, and if these are not found in existing lexicons the grapheme-to-phoneme conversion is applied. In Xxxxxx et al. (1998) it was found that the number of insertions (4 per cent) was much sma...
Automatic Methods. With Orthography
5.2.2.2.1 With Orthography, Canonical Transcriptions Probably the simplest way to derive phonological transcriptions in this case is by using canonical transcriptions (see above). Once a phonological (canonical) transcription is obtained for every word, the orthographic representations are simply replaced by the corresponding phonological representations (Binnenpoorte and Cucchiarini 2003; van Bael et al. 2006, 2007).
5.2.2.2.2 With Orthography, Forced Recognition Words are not always pronounced in the same way, and thus representing all occurrences of a word with the same phonological transcription will result in phonological transcriptions containing errors. The quality of the phonological transcriptions could be improved by modelling pronunciation variation. One way to do this is to use so-called forced recognition. In forced recognition the goal is not to recognize the string of words that was spoken, as in standard ASR. On the contrary, in forced recognition this string of words (the orthographic transcription) has to be known. Given the orthographic transcription, and multiple pronunciations of some words, forced recognition will determine automatically which of the pronunciation variants of a word best matches the audio signal corresponding to that word. The words are thus fixed, and for every word the recognizer is forced to choose one of the pronunciation variants of that word—hence the term ‘forced recognition’. The search space can also be represented as a network or lattice with pronunciation variants. The goal then is to find the optimal path in that network, the optimal alignment, by means of the Viterbi algorithm; this is why this procedure is also referred to as ‘Viterbi’ or ‘forced’ alignment. In any case, if hypotheses (pronunciation variants) are present, forced recognition can be used for hypothesis verification (i.e. to find the hypothesis, the variant that most closely matches the audio signal). It is important to note that through the use of pronunciation variants it is also possible to model sandhi phenomena and cross-word phenomena such as assimilation or intrusion. We evaluated how well forced recognition performs by comparing its performance to that of human annotators (Xxxxxx et al. 2001). Nine experts, who often carried out phonetic transcriptions for their own research, carried out exactly the same task as the computer program: they had to indicate which pronunciation variants of a word best matched the audio ...
