In order to stave off the effects of hypoxia, speech may become limited at elevated altitudes. This paper evaluates the role of speech on acoustic and physiological features used to detect hypoxia. Acoustic, cerebral blood oxygenation, and cardiac signals were recorded from participants who completed control and normobaric hypoxia experimental conditions. Acoustic and physiological features were extracted from (non-)speech segments via a voice activity detection method. Support Vector Machines were used to evaluate hypoxia classification using independent and combined features produced at sea-level and simulated 5 km altitudes. Models were built upon a 4fold cross-validation design and evaluated on an independent dataset. Our results confirmed the importance of physiological features when detecting hypoxia. When combined, acoustic features boosted performance by 10% at 5 km in comparison to sea-level. Hypoxia detection may be improved by distinguishing respiration from non-speech.