Super Monotonic Alignment Search
Monotonic alignment search (MAS), introduced by Glow-TTS, is one of the most popular algorithm in TTS 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 paths, the time complexity of the algorithm is $O(T \times S)$. 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 \url{https://github.com/supertone-inc/super-monotonic-align}.
Code (1)
Tasks
CPUGPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improvement in Sign Language Translation Using Text CTC Alignment
Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language v…
Sign Language TranslationTransfer LearningTranslationGlow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantages, the parallel TTS models cannot be trained without guidan…
text-to-speechText to SpeechText-To-Speech SynthesisNon-Monotonic Sentence Alignment via Semisupervised Learning
Learning Monotonic Attention in Transducer for Streaming Generation
Streaming generation models are increasingly utilized across various fields, with the Transducer architecture being particularly popular in industrial applications. However, its input-synchronous decoding mechanism prese…
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word …
Machine TranslationSentenceTranslation