The phrase "amount of utterances" is not correct in standard written English.
The word "amount" is typically used with uncountable nouns, while "utterances" is a countable noun, so "number of utterances" would be more appropriate.
Example: "The number of utterances in the conversation was surprisingly high."
Alternatives: "count of utterances" or "total utterances".
This shows the negative impact that the reduced amount of utterances by disabled speakers had in the previously discussed experimental results.
If two counsellors were present, characteristics of the counsellor with the largest amount of utterances during the visit were used.
During the 37 visits out of 130 that were conducted by a clinical geneticist together with a resident or a nurse, the counsellor with the largest amount of utterances averaged 468.4 statements (s.d.=162.9; min.=199, max.=821), compared to a mean of 138.5 utterances by the other counsellor (s.d.=85.5; min.=6, max.=369).=369
In the case of word units and very large vocabulary, in order to train necessary decision trees, a huge amount of speech utterances are required.
The average WERs of SimData and RealData are calculated as (sum _{text {set}} (mathrm {W_{textit {ER}}} cdot N_{text {utt}}) / sum N_{text {utt}}), where W ER represents WER of each test set with the corresponding amount of test utterances N utt.
Our minds are racing, computing, inferring, referring, composing, reflecting, rejecting ten thousand times a minute, and all that an objective observer is privy to is the relative infinitesimal amount of public utterances, writings and other forms of "speech" we care to share with others.
The total number of utterances was 400.
% = percent of total number of utterances.
With those approaches, a mapping function is trained in advance using a small amount of training data consisting of utterance pairs consisting of source and target voices.
We think that the reduced performance improvements in the KPOW task are mainly resulted from the reason that because the adaptation is performed on a single utterance basis, the amount of adaptation data in each test utterance becomes not enough to fully adapt the much larger number of acoustic models in this large vocabulary task.
