{"ID":2921576,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T04:50:26.150571705Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01009","arxiv_id":"2606.01009","title":"MelT: GEMM-Native NDFT for Efficient Single-Stage Audio Frontends on Modern Accelerators","abstract":"Modern audio processing networks are commonly deployed on accelerators whose peak throughput is obtained through dense linear algebra, whereas conventional acoustic frontends -- a Short-Time Fourier Transform (STFT) followed by sparse Mel aggregation -- remain structurally heterogeneous. This mismatch can introduce memory-bandwidth, dispatch, and intermediate-allocation overheads on contemporary accelerator backends. This work introduces MelT, a single-stage frontend framework in which Mel-spaced Non-Uniform Discrete Fourier Transform (NDFT) bases are precomputed and applied to time-domain acoustic frames through dense General Matrix Multiplication (GEMM) operations. The contribution is not the NDFT operator itself; rather, it is the formulation of Mel-spaced NDFT projection as a GEMM-native audio frontend and its evaluation as a hardware-efficient alternative to conventional STFT+Mel pipelines. Evaluated across platforms ranging from Apple A18 Pro edge hardware to NVIDIA H100 datacenter acceleration, MelT attains up to a $3.75\\times$ speedup in inference latency and a $3.52\\times$ reduction in energy consumption while maintaining downstream classification accuracy.","short_abstract":"Modern audio processing networks are commonly deployed on accelerators whose peak throughput is obtained through dense linear algebra, whereas conventional acoustic frontends -- a Short-Time Fourier Transform (STFT) followed by sparse Mel aggregation -- remain structurally heterogeneous. This mismatch can introduce mem...","url_abs":"https://arxiv.org/abs/2606.01009","url_pdf":"https://arxiv.org/pdf/2606.01009v1","authors":"[\"Augusto Camargo\",\"Marcelo Finger\"]","published":"2026-05-31T04:53:12Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[]","has_code":false}