MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline

Song generation aims to produce full songs with vocals and accompaniment from lyrics and text descriptions, yet end-to-end models remain data- and compute-intensive and provide limited editability. We advocate a compositional alternative that decomposes the task into melody composition, singing voice synthesis, and singing accompaniment generation. Central to our approach is MIDI-informed singing accompaniment generation (MIDI-SAG), which conditions accompaniment on the symbolic vocal-melody MIDI to improve rhythmic and harmonic alignment between singing and instrumentation. Moreover, beyond conventional SAG settings that assume continuously sung vocals, compositional song generation features intermittent vocals; we address this by combining explicit rhythmic/harmonic controls with audio continuation to keep the backing track consistent across vocal and non-vocal regions. With lightweight newly trained components requiring only 2.5k hours of audio on a single RTX 3090, our pipeline approaches the perceptual quality of recent open-source end-to-end baselines in several metrics. We provide audio demos and will open-source our model at https://composerflow.github.io/web/.

Linguistically Informed Evaluation of Multilingual ASR for African Languages

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By contrast, Feature Error Rate (FER) has recently attracted attention as a viable metric that reveals linguistically meaningful errors in models' performance. In this paper, we evaluate three speech encoders on two African languages by complementing WER with CER, and FER, and add a tone-aware extension (TER). We show that by computing errors on phonological features, FER and TER reveal linguistically-salient error patterns even when word-level accuracy remains low. Our results reveal that models perform better on segmental features, while tones (especially mid and downstep) remain the most challenging features. Results on Yoruba show a striking differential in metrics, with WER=0.788, CER=0.305, and FER=0.151. Similarly for Uneme (an endangered language absent from pretraining data) a model with near-total WER and 0.461 CER achieves the relatively low FER of 0.267. This indicates model error is often attributable to individual phonetic feature errors, which is obscured by all-or-nothing metrics like WER.