Speech basis fashions have lately achieved outstanding capabilities throughout a variety of duties. Nevertheless, their analysis stays disjointed throughout duties and mannequin sorts. Totally different fashions excel at distinct facets of speech processing and thus require completely different analysis protocols. This paper proposes a unified taxonomy that addresses the query: Which analysis is acceptable for which mannequin? The taxonomy defines three orthogonal axes: the analysis facet being measured, the mannequin capabilities required to try the duty, and the duty or protocol necessities wanted to carry out it. We classify a broad set of current evaluations and benchmarks alongside these axes, spanning areas similar to illustration studying, speech era, and interactive dialogue. By mapping every analysis to the capabilities a mannequin exposes (e.g., speech era, real-time processing) and to its methodological calls for (e.g., fine-tuning information, human judgment), the taxonomy gives a principled framework for aligning fashions with appropriate analysis strategies. It additionally reveals systematic gaps, similar to restricted protection of prosody, interplay, or reasoning, that spotlight priorities for future benchmark design. Total, this work provides a conceptual basis and sensible information for choosing, deciphering, and lengthening evaluations of speech fashions.
