Moto Hira — accepted AI-conference papers

2024

Less Peaky and More Accurate CTC Forced Alignment by Label Priors

Ruizhe Huang, Xiaohui Zhang, Zhaoheng Ni, Li Sun, Moto Hira, Jeff Hwang +6

ICASSP 2024accepted

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at allevia…

Cited by 0 Source ↗Scholar ↗

2022

Torchaudio: Building Blocks for Audio and Speech Processing

Yao-Yuan Yang, Moto Hira, Zhaoheng Ni, Artyom Astafurov, Caroline Chen, Christian Puhrsch +12

ICASSP 2022accepted

This document describes version 0.10 of TorchAudio: building blocks for machine learning applications in the audio and speech processing domain. The objective of TorchAudio is to accelerate the development and deployment of machine learning applications for researchers and engineers by providing off…

Cited by 0 Source ↗Scholar ↗