Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming
Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing robustness across diverse acoustic conditions and languages. In contrast, Forced Alignment has not experienced comparable progress, and traditional HMM-GMM frameworks remain widely adopted and highly competitive. To address this gap, we propose an end-to-end, fully differentiable neural architecture specifically designed for phoneme alignment. The model consists of an encoder that processes the input signal and a decoder that produces alignment decisions. The encoder is structured into two complementary branches: one dedicated to phoneme identity verification and the other to phoneme boundary detection. The decoder is implemented as a trainable module based on differentiable soft dynamic programming. The entire system is optimized end-to-end using a novel contrastive loss that encourages clear separation between steady-state phoneme regions and transition boundaries. The proposed approach outperforms the current state of the art in phoneme alignment on hand-annotated English benchmarks, achieves strong word-level generalization results, and demonstrates generalization on unseen languages.
Code (0)
등록된 구현이 없습니다.
Tasks
Boundary DetectionSimilar Papers 제목 키워드 기반
Greek Forced Alignment: Assessing the Accuracy of the Montreal Forced Aligner
Forced alignment has allowed for the rapid creation and annotation of corpora. In this study we examine the Montreal Foreced Aligner and its accuracy of aligning Greek data. Using a conversational Greek corpus we train a…
Soft-DTW: a Differentiable Loss Function for Time-Series
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable siz…
Dynamic Time WarpingTime SeriesTime Series AnalysisStabilizing Training with Soft Dynamic Time Warping: A Case Study for Pitch Class Estimation with Weakly Aligned Targets
Soft dynamic time warping (SDTW) is a differentiable loss function that allows for training neural networks from weakly aligned data. Typically, SDTW is used to iteratively compute and refine soft alignments that compens…
Dynamic Time WarpingSchedulingDeep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW). Existing approaches to differentiable DTW either differentiate through a fixed w…
Dynamic Time WarpingInformation RetrievalMusic Information RetrievalRetrieval+2Soft-MSM: Differentiable Context-Aware Elastic Alignment for Time Series
Elastic distances like dynamic time warping (DTW) are central to time series machine learning because they compare sequences under local temporal misalignment. Soft-DTW is an adaptation of DTW that can be used as a gradi…