It depends on the range of your scores for the two modalities. If one is binary, for example, while the other is decimal, then score normalization is definitely needed. Think you should consider the classifier used and their output scores, rather than the feature extractor.

Please read this for a good primer

Anil Jain, Karthik Nandakumar, Arun Ross, Score normalization in multimodal biometric systems, Pattern Recognition, Volume 38, Issue 12, December 2005, Pages 2270-2285, ISSN 0031-3203, http://dx.doi.org/10.1016/j.patcog.2005.01.012.

(http://www.sciencedirect.com/science/article/pii/S0031320305000592)

Abstract: Multimodal biometric systems consolidate the evidence presented by multiple biometric sources and typically provide better recognition performance compared to systems based on a single biometric modality. Although information fusion in a multimodal system can be performed at various levels, integration at the matching score level is the most common approach due to the ease in accessing and combining the scores generated by different matchers. Since the matching scores output by the various modalities are heterogeneous, score normalization is needed to transform these scores into a common domain, prior to combining them. In this paper, we have studied the performance of different normalization techniques and fusion rules in the context of a multimodal biometric system based on the face, fingerprint and hand-geometry traits of a user. Experiments conducted on a database of 100 users indicate that the application of min–max, z-score, and tanh normalization schemes followed by a simple sum of scores fusion method results in better recognition performance compared to other methods. However, experiments also reveal that the min–max and z-score normalization techniques are sensitive to outliers in the data, highlighting the need for a robust and efficient normalization procedure like the tanh normalization. It was also observed that multimodal systems utilizing user-specific weights perform better compared to systems that assign the same set of weights to the multiple biometric traits of all users.

Keywords: Biometrics; Multibiometrics; Score normalization; Face; Fingerprint; Hand-geometry; Tanh; Min–max; z-score; Sigmoid; Parzen; User-specific weights

If the range of the feature is different in different modalities and one is going to use some sort comparative analysis, it is always safe to normalise the features.

Moreover, often the feature set makes more sense and is easily interpretable in the normalized form.