paper-with-me

Papers

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment

2020-10-24 · NAACL 2021 4 · Ethan A. Chi, Julian Salazar, Katrin Kirchhoff

Non-autoregressive models greatly improve decoding speed over typical sequence-to-sequence models, but suffer from degraded performance. Infilling and iterative refinement models make up some of this gap by editing the outputs of a non-autoregressive model, but are constrained in the edits that they can make. We propose iterative realignment, where refinements occur over latent alignments rather than output sequence space. We demonstrate this in speech recognition with Align-Refine, an end-to-end Transformer-based model which refines connectionist temporal classification (CTC) alignments to allow length-changing insertions and deletions. Align-Refine outperforms Imputer and Mask-CTC, matching an autoregressive baseline on WSJ at 1/14th the real-time factor and attaining a LibriSpeech test-other WER of 9.0% without an LM. Our model is strong even in one iteration with a shallower decoder.

📄 PDF Abstract BibTeX arXiv:2010.14233

Code (0)

등록된 구현이 없습니다.

Tasks

Decoderspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling

2026-02-09 · Ziyang Cheng, Yuhao Wang, Heyang Liu, Ronghua Wu 외 arxiv

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation ef…

A Non-autoregressive Model for Joint STT and TTS

2025-01-15 · Vishal Sunder, Brian Kingsbury, George Saon, Samuel Thomas 외

In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the spee…

Automatic Speech Recognitionspeech-recognitionSpeech RecognitionSpeech Synthesis

Imputer: Sequence Modelling via Imputation and Dynamic Programming

2020-02-20 · ICML 2020 1 · William Chan, Chitwan Saharia, Geoffrey Hinton, Mohammad Norouzi 외

This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations. The Imputer is an iterative generative model, requiring only a constant number of generation steps ind…

Imputationspeech-recognitionSpeech Recognition

Diffusion Large Language Models for Visual Speech Recognition

2026-05-27 · Jeong Hun Yeo, Chae Won Kim, Hyeongseop Rha, Yong Man Ro arxiv

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose…

Visual Speech Recognition

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

2021-06-17 · Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss 외

This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence…

Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis