mlsanityData to 14 Oct 2026

Super Monotonic Alignment Search

arXiv 2409.07704 ↗First posted 12 Sep 2024eess.AS cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Monotonic alignment search (MAS), introduced by Glow-TTS, is one of the most popular algorithm in text-to-speech to estimate unknown alignments between text and speech. Since this algorithm needs to search for the most probable alignment with dynamic programming by caching all possible paths, the time complexity of the algorithm is O(T × S), where T is the length of text and S is the length of speech representation. The authors of Glow-TTS run this algorithm on CPU, and while they mentioned it is difficult to parallelize, we found that MAS can be parallelized in text length dimension and CPU execution consumes an inordinate amount of time for inter-device copy. Therefore, we implemented a Triton kernel and PyTorch JIT script to accelerate MAS on GPU without inter-device copy. As a result, Super-MAS Triton kernel is up to 72 times faster in the extreme-length case. The code is available at https://github.com/supertone-inc/super-monotonic-align.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

11 of 18 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  4. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  5. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  6. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  7. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
  8. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  9. 2022NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesiscited by 38
  10. 2024DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidancecited by 11
  11. 2023PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTScited by 4

Built on by

Not cited yet.